© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50374
    Prev
    Next
    INDEX
    Explanations

    the Mets

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

    symbols and separators

    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
     веществ
    0.47
     গানের
    0.46
     причин
    0.45
     Conversations
    0.45
     причина
    0.44
     conversa
    0.44
     Stow
    0.43
    ৷
    0.43
     unintentional
    0.42
     основы
    0.42
    POSITIVE LOGITS
    iqu
    0.47
    🎾
    0.46
    🏒
    0.46
    ipas
    0.45
     juegos
    0.45
    💹
    0.45
    O
    0.44
    indx
    0.44
    liquer
    0.44
     permitirá
    0.44
    Activations Density 0.000%

    No Known Activations