© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1588
    Prev
    Next
    INDEX
    Explanations

    contractions like don't haven't didn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coverageStat
    1.27
    <unused765>
    1.23
    clientsdetails
    1.20
    䒷
    1.20
    destroyEach
    1.19
    lockSeconds
    1.18
    <unused1173>
    1.17
    捌章
    1.17
    aeskeygenassist
    1.17
    <unused1182>
    1.17
    POSITIVE LOGITS
    s
    1.05
     We
    0.93
    We
    0.92
     Be
    0.82
     presidente
    0.81
    S
    0.80
     G
    0.79
     You
    0.79
    K
    0.78
    You
    0.78
    Activations Density 1.134%

    No Known Activations