© 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. 144786
    Prev
    Next
    INDEX
    Explanations

    with local

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

    Values Alignment

    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
    估
    0.46
    隨
    0.46
    繪
    0.45
     Фили
    0.45
    ந்தார்
    0.45
    各有
    0.44
     Эр
    0.44
    ፩
    0.43
     generals
    0.43
    अनि
    0.43
    POSITIVE LOGITS
    та
    0.51
    的企业
    0.46
    า
    0.46
     doanh
    0.46
     tais
    0.46
    Investing
    0.45
    tais
    0.44
     ডাউনলোড
    0.44
     modeli
    0.44
    as
    0.43
    Activations Density 0.001%

    No Known Activations