© 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. 203892
    Prev
    Next
    INDEX
    Explanations

    setting or starting

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

    subspace learning foundation

    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
    л
    0.48
     называ
    0.47
     diagnóstico
    0.47
     nadie
    0.45
     идентифика
    0.45
    ށް
    0.44
     привле
    0.44
     traduc
    0.44
    ரசுக்
    0.44
     pú
    0.44
    POSITIVE LOGITS
     高校
    0.47
     吴
    0.45
     अपना
    0.44
    getOutputStream
    0.44
    <0xE3>
    0.43
     就
    0.43
     हों
    0.42
    지가
    0.41
    要想
    0.41
     ہوں
    0.40
    Activations Density 0.001%

    No Known Activations