© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10032
    Prev
    Next
    INDEX
    Explanations

    glycogen stores

    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
    ку
    2.51
    Как
    2.24
    е
    2.19
     üst
    2.05
    ies
    1.98
     sido
    1.92
    邝
    1.84
     dap
    1.84
    ing
    1.82
     puncak
    1.82
    POSITIVE LOGITS
    &\
    2.40
    ্সের
    2.37
    ্স
    2.30
    েশ
    2.27
    pesar
    2.17
    ことができる
    2.13
    noon
    2.10
    র
    2.09
    &=\
    2.05
    dashed
    2.05
    Activations Density 0.006%

    No Known Activations