© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    copyright text

    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_22_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
    刑
    0.75
    emt
    0.74
    intro
    0.74
    urgent
    0.73
    which
    0.72
    gt
    0.72
     colis
    0.71
    sided
    0.71
    from
    0.71
     >>
    0.70
    POSITIVE LOGITS
     William
    1.07
     Robert
    1.07
     Joseph
    1.06
     Patrick
    1.06
     Walter
    1.05
     Association
    1.05
     Corporation
    1.04
     Cognitive
    1.04
     Christopher
    1.03
     David
    1.03
    Activations Density 0.005%

    No Known Activations