© 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. 11621
    Prev
    Next
    INDEX
    Explanations

    superhero, partner, ocean, rock

    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
     pursuant
    0.82
     فونب
    0.79
     zapewnia
    0.75
     וכ
    0.72
    <unused2189>
    0.72
     وړاندوین
    0.71
     بیٹنگ
    0.71
     וש
    0.70
     TestAvg
    0.70
    िंक
    0.69
    POSITIVE LOGITS
     the
    1.02
    D
    0.95
     a
    0.91
     다른
    0.88
     A
    0.87
    N
    0.87
     Deus
    0.86
     alcuni
    0.86
    B
    0.83
    A
    0.83
    Activations Density 0.279%

    No Known Activations