© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1702
    Prev
    Next
    INDEX
    Explanations

    conversational turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
     alliances
    1.01
     petitions
    0.98
    сторі
    0.97
     praised
    0.96
    ̋
    0.96
    ႈ
    0.96
     confided
    0.96
     mesi
    0.93
     quotid
    0.93
    陟
    0.93
    POSITIVE LOGITS
    Battle
    0.83
    ולי
    0.81
    Inspector
    0.81
     androidx
    0.81
    ع
    0.80
    DQ
    0.80
    OK
    0.79
     notoriously
    0.78
    น์
    0.78
    ким
    0.77
    Activations Density 0.949%

    No Known Activations