© 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. 89617
    Prev
    Next
    INDEX
    Explanations

    rebuilding your home

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

    male, female, or spectrum

    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
    Used
    0.51
     Used
    0.46
    0.45
     ചുമ
    0.44
     ブ
    0.44
    BSP
    0.44
    ウ
    0.44
     pum
    0.43
     ラ
    0.43
     Rudd
    0.43
    POSITIVE LOGITS
    ச்சியை
    0.44
    가가
    0.44
     fandom
    0.43
    ຈາກ
    0.42
    হত্যার
    0.42
    气
    0.42
    ກ
    0.42
    மையை
    0.41
    หุ้น
    0.41
    没办法
    0.41
    Activations Density 0.000%

    No Known Activations