© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    momentarily paused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     (
    1.34
     mother
    1.28
     families
    1.25
     moms
    1.19
     parents
    1.16
     quart
    1.13
    /
    1.12
     deposit
    1.06
     books
    1.06
     mama
    1.06
    POSITIVE LOGITS
     tłumac
    2.30
     posicion
    2.25
    랭
    2.24
     snel
    2.18
     이러
    2.12
    znym
    2.11
     دفاع
    2.11
    Tact
    2.11
    millis
    2.11
     useContext
    2.10
    Activations Density 0.018%

    No Known Activations