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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12144
    Prev
    Next
    INDEX
    Explanations

    against government snoops

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     will
    -1.66
     having
    -1.45
     with
    -1.39
     for
    -1.25
    ׇ
    -1.20
     but
    -1.19
     there
    -1.17
    取締
    -1.12
     obviously
    -1.12
     excellent
    -1.10
    POSITIVE LOGITS
     felicitación
    1.16
     useAuth
    1.15
     altavoz
    1.11
     استناد
    1.09
    hri
    1.09
    уд
    1.09
     spodnie
    1.08
    illige
    1.07
     ที่
    1.07
    exemple
    1.05
    Activations Density 0.089%

    No Known Activations