© 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. 83965
    Prev
    Next
    INDEX
    Explanations

    descriptions, tips, and visual sources

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

    writing titles and code

    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
    djang
    0.45
    CString
    0.45
     держав
    0.44
    みが
    0.43
     punctato
    0.43
    OnFileChange
    0.43
    登
    0.42
    rägen
    0.42
    ینی
    0.42
    PlatformImage
    0.42
    POSITIVE LOGITS
    encia
    0.55
     laman
    0.46
     ته
    0.45
    -
    0.45
    idu
    0.44
    ه
    0.43
    的用户
    0.42
    <0xA5>
    0.42
    ostat
    0.42
    udes
    0.41
    Activations Density 0.000%

    No Known Activations