© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11423
    Prev
    Next
    INDEX
    Explanations

    generic messages are a turn-off

    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_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
    ριθ
    1.70
    齢
    1.70
    ive
    1.56
    ാള
    1.54
    fold
    1.53
    ças
    1.50
    is
    1.50
    عي
    1.48
    ic
    1.48
    ഷ്ട
    1.48
    POSITIVE LOGITS
    󠁢
    2.10
     сви
    2.09
     үз
    2.06
     seagulls
    1.94
    audioType
    1.94
    iverr
    1.92
    netty
    1.91
    bserv
    1.91
    Влади
    1.89
    𝓂
    1.88
    Activations Density 0.003%

    No Known Activations