© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    in leadership or seen

    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
    <unused2058>
    1.17
     confertim
    1.16
    lblCredits
    1.15
     TextStyle
    1.15
    <unused1876>
    1.15
    <unused1793>
    1.13
     honoured
    1.13
    ScriptInterface
    1.13
     Acá
    1.12
     ngắn
    1.11
    POSITIVE LOGITS
    a
    1.04
    ো
    1.02
    ן
    1.02
    ست
    0.96
    and
    0.95
    ő
    0.93
    ش
    0.91
    ons
    0.91
    <0x0D>
    0.91
    на
    0.91
    Activations Density 0.000%

    No Known Activations