© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4096
    Prev
    Next
    INDEX
    Explanations

    even more details

    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
     stepping
    1.78
     steep
    1.65
    ->_
    1.64
     spelled
    1.64
     adjusting
    1.63
     owning
    1.61
     sluggish
    1.57
    duled
    1.56
     adjusted
    1.54
     accepting
    1.54
    POSITIVE LOGITS
    Repost
    2.66
    MeToo
    2.38
    AppCompatTheme
    2.35
    ################
    2.19
    তঃ
    2.16
    場合には
    2.04
    ######
    2.03
    উন
    2.00
    HairColor
    1.93
     noqa
    1.93
    Activations Density 0.034%

    No Known Activations