© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58502
    Prev
    Next
    INDEX
    Explanations

    project initiator crowdfunding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     court
    -0.72
     monde
    -0.67
     world
    -0.64
    邂
    -0.62
     acting
    -0.62
     زیست
    -0.60
    acting
    -0.60
    dataclass
    -0.60
     gamme
    -0.58
    Página
    -0.58
    POSITIVE LOGITS
    pulos
    0.74
    irected
    0.73
     invokingState
    0.69
    이블
    0.69
     arşivlendi
    0.68
    cree
    0.68
    Eerste
    0.68
     splice
    0.68
     salió
    0.68
    štění
    0.68
    Activations Density 0.055%

    No Known Activations