© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65920
    Prev
    Next
    INDEX
    Explanations

    animal names

    np_acts-logits-general · gemini-2.5-flash-lite

    references to Eagle (whether as a software product, scout rank, sports team, or bird).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates specifically on occurrences of the word “Eagle” (including its plural form).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .........
    -2.34
    ING
    -2.19
    T
    -2.17
     accolades
    -2.17
    ...........
    -2.17
    艄
    -2.16
    G
    -2.14
    會有
    -2.13
     plongée
    -2.13
    誂
    -2.11
    POSITIVE LOGITS
    </i>
    2.39
     abbildung
    2.36
    these
    2.34
    </td>
    2.22
     the
    2.20
    彞
    2.09
    ’,
    2.03
     Tonnen
    2.03
     größer
    2.02
    菀
    2.02
    Activations Density 0.053%

    No Known Activations