© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11883
    Prev
    Next
    INDEX
    Explanations

    approximate word counts

    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_7_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
     imaju
    2.35
    szer
    2.31
    슭
    2.25
    świet
    2.17
     predstavlja
    2.07
    ൧
    2.07
    呸
    2.07
    国産
    2.07
     대표
    2.03
     contatto
    2.03
    POSITIVE LOGITS
     Boring
    2.13
     Alla
    1.84
    amenti
    1.75
    命令
    1.74
    guards
    1.70
    wwww
    1.69
    yyyyyyyy
    1.68
     force
    1.67
     incarceration
    1.65
     atrocities
    1.63
    Activations Density 0.013%

    No Known Activations