© 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. 11192
    Prev
    Next
    INDEX
    Explanations

    BSD license

    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
    ק
    3.41
    er
    2.35
    на
    2.31
    tn
    2.15
    it
    2.08
    اح
    2.03
    اي
    2.02
    ात
    1.98
    ties
    1.97
    or
    1.96
    POSITIVE LOGITS
    𝗿
    2.53
     lymphomas
    2.35
    м
    2.31
    𝗱
    2.21
    𝗮
    2.21
    𝗗
    2.19
    𝗴
    2.19
    𝗶
    2.18
    𝗰
    2.17
     נע
    2.14
    Activations Density 0.001%

    No Known Activations