© 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. 10-GEMMASCOPE-RES-131K
    7. 44284
    Prev
    Next
    INDEX
    Explanations

    mimic or emulate

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

    The neuron consistently lights up on semantically central content words—especially technical or topic‐specific nouns and verbs—rather than on common function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     =
    -1.49
     حتی
    -1.19
     tiež
    -1.14
    chengladbach
    -1.12
    એ
    -1.11
    })$,
    -1.08
     miasto
    -1.06
    bija
    -1.05
    ;//
    -1.05
    ácii
    -1.05
    POSITIVE LOGITS
     with
    1.96
     a
    1.51
     vence
    1.20
     แดง
    1.20
    awarkan
    1.19
     things
    1.19
     heerlijk
    1.19
     custa
    1.17
     both
    1.13
     somebody
    1.12
    Activations Density 0.090%

    No Known Activations