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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23885
    Prev
    Next
    INDEX
    Explanations

    knocking, struck, impact

    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_34/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
     parking
    -0.77
    indo
    -0.76
    いや
    -0.75
    lo
    -0.75
     Leiter
    -0.72
    ktionen
    -0.72
    માં
    -0.72
    {:
    -0.71
     viena
    -0.71
    los
    -0.70
    POSITIVE LOGITS
     knocking
    1.20
    Knock
    1.19
     Knock
    1.16
    knock
    1.12
     knock
    1.10
     at
    1.05
     pounding
    1.02
     Kno
    1.01
    Kno
    0.95
     knocks
    0.83
    Activations Density 0.006%

    No Known Activations