© 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. 2254
    Prev
    Next
    INDEX
    Explanations

    social interactions and behaviors

    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
    ه
    4.15
    ل
    3.88
    ו
    3.39
    o
    3.17
    ن
    3.05
    at
    2.93
    as
    2.87
    ν
    2.82
     detonations
    2.73
    ся
    2.72
    POSITIVE LOGITS
    ων
    2.72
    साइटी
    2.71
    t
    2.62
     preto
    2.55
    夠
    2.52
     acutely
    2.48
    सायटी
    2.48
     lleno
    2.41
    கூ
    2.32
     adept
    2.31
    Activations Density 0.087%

    No Known Activations