© 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. 196857
    Prev
    Next
    INDEX
    Explanations

    services, museum, prison, choose

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

    delphi program

    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
    ↵↵
    0.51
     identification
    0.47
    ↵
    0.46
    <0x0D>
    0.46
     Terms
    0.46
     founding
    0.44
     SC
    0.44
     “
    0.43
     Ra
    0.43
     Weak
    0.43
    POSITIVE LOGITS
    ЕТ
    0.60
    سلم
    0.58
    𝟖
    0.56
     Волго
    0.56
    បញ្ចូល
    0.55
    澈
    0.54
    侣
    0.54
    시켜
    0.53
     которым
    0.52
    йи
    0.52
    Activations Density 0.000%

    No Known Activations