© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4204
    Prev
    Next
    INDEX
    Explanations

    amount of effort, time, or change

    np_acts-logits-general · gemini-2.5-flash-lite

    effort, cost, or significant change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ماشینونو
    0.26
    használ
    0.24
    删除
    0.24
     wenden
    0.23
     उन्हें
    0.23
    }}$.
    0.22
     þei
    0.22
    IZE
    0.22
    を使用
    0.21
    izability
    0.21
    POSITIVE LOGITS
     more
    0.38
     гораздо
    0.32
     much
    0.32
     less
    0.32
     tremendous
    0.31
     huge
    0.29
     enough
    0.29
     quite
    0.29
     a
    0.28
     great
    0.28
    Activations Density 0.616%

    No Known Activations