© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    yes or no responses

    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
    Appearance
    1.67
    @
    1.65
    Timelapse
    1.62
    Lifetime
    1.60
    lifetime
    1.59
    #
    1.58
    About
    1.58
    以來
    1.56
     Engineered
    1.56
    day
    1.56
    POSITIVE LOGITS
     enl
    1.23
     sans
    1.14
    结
    1.12
    IZE
    1.10
     schn
    1.06
     wi
    1.05
     Schn
    1.04
     cris
    1.04
    боль
    1.04
    消
    1.03
    Activations Density 0.008%

    No Known Activations