© 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. 11159
    Prev
    Next
    INDEX
    Explanations

    the frailty

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

    MMLU benchmark

    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
    ibi
    0.47
    옆
    0.46
     옆
    0.45
    欧美
    0.43
     전국
    0.43
    nij
    0.43
    óg
    0.42
    میر
    0.42
    סי
    0.40
    iosi
    0.40
    POSITIVE LOGITS
     thrombo
    0.48
     শিকার
    0.47
    。(
    0.47
     поступ
    0.46
    ្រី
    0.46
    ।...
    0.45
    貳
    0.45
     xw
    0.44
     gleaming
    0.44
     கவு
    0.43
    Activations Density 0.000%

    No Known Activations