© 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-262K
    7. 12061
    Prev
    Next
    INDEX
    Explanations

    past states or actions

    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_262k_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
    ৬
    2.64
     fleste
    2.63
    ════
    2.49
     fechas
    2.45
    bbene
    2.34
     Eligible
    2.28
    𝘸
    2.23
     bien
    2.22
     вот
    2.21
    [['
    2.18
    POSITIVE LOGITS
    n
    5.53
    н
    5.05
    ن
    4.94
    a
    4.89
    ل
    4.82
    ه
    4.77
    o
    4.50
    m
    4.28
    y
    4.27
    ে
    4.17
    Activations Density 0.033%

    No Known Activations