© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    histogram processing

    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
    ))))
    1.64
    $("#
    1.58
     "");
    1.57
    κι
    1.51
    ্লাহ
    1.50
     बातम्या
    1.47
    )))
    1.45
    $.
    1.44
     dàng
    1.40
     ode
    1.38
    POSITIVE LOGITS
    न
    1.92
    ১৮
    1.79
    ా
    1.70
    ার
    1.70
    ن
    1.67
    ারী
    1.65
    प्रोड
    1.65
    ﺯ
    1.64
    心
    1.63
    აც
    1.63
    Activations Density 0.003%

    No Known Activations