© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 823
    Prev
    Next
    INDEX
    Explanations

    referring to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    1.23
     suffices
    1.09
     dauert
    1.01
     Reveals
    1.01
    matches
    0.99
     Stops
    0.97
     consumes
    0.97
     Firmen
    0.95
    ie
    0.95
     excludes
    0.95
    POSITIVE LOGITS
     gonna
    1.28
     not
    1.17
     proud
    1.16
    <unused2130>
    1.13
     going
    1.13
     actually
    1.12
     able
    1.12
     fortunate
    1.11
     actively
    1.08
    <unused2172>
    1.07
    Activations Density 0.740%

    No Known Activations