© 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. 6995
    Prev
    Next
    INDEX
    Explanations

    almost all/entirely

    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
     lspace
    1.39
     +/-
    1.33
    biggl
    1.32
    +/-
    1.26
    WhiteElo
    1.24
     ±
    1.23
    十一
    1.20
    
    1.20
     +-
    1.18
     shortfall
    1.15
    POSITIVE LOGITS
     alltid
    2.75
     altid
    2.57
     sempre
    2.42
     siempre
    2.36
     всегда
    2.34
     завжди
    2.32
    ทุกคน
    2.32
     ALWAYS
    2.30
     vždy
    2.27
    always
    2.25
    Activations Density 0.039%

    No Known Activations