© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
    hii
    -0.74
    Tony
    -0.70
    bottomRight
    -0.68
    wl
    -0.68
    Follow
    -0.68
    grafo
    -0.68
    Jennifer
    -0.67
     Ven
    -0.67
    ivis
    -0.67
    ven
    -0.67
    POSITIVE LOGITS
    貴重
    0.71
     Oda
    0.71
     Cout
    0.70
    Leod
    0.70
    ularis
    0.68
    KeyName
    0.68
    Embal
    0.66
    Área
    0.65
    Embedded
    0.65
    ácie
    0.64
    Activations Density 0.058%

    No Known Activations