© 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. 33456
    Prev
    Next
    INDEX
    Explanations

    entities and their states

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

    The neuron responds to semantically rich content words (mainly nouns and verbs) rather than function words.

    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
     and
    -1.37
     or
    -1.29
     with
    -1.27
     abund
    -1.13
    Также
    -1.09
    ционного
    -1.06
     +'
    -1.05
     незавер
    -1.04
     tamb
    -1.02
     extraordin
    -1.02
    POSITIVE LOGITS
     largely
    1.49
     mainly
    1.34
     somewhat
    1.30
     either
    1.16
     normally
    1.11
     abbastanza
    1.08
     monté
    1.08
     simply
    1.08
     zwar
    1.07
    iramente
    1.02
    Activations Density 0.080%

    No Known Activations