© 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. 77953
    Prev
    Next
    INDEX
    Explanations

    hidden gems and artists

    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
     claudia
    -0.81
     eene
    -0.79
    ーター
    -0.79
     minera
    -0.77
    indices
    -0.77
    への
    -0.76
     pappa
    -0.75
     burch
    -0.75
     interro
    -0.75
     tarte
    -0.75
    POSITIVE LOGITS
     hidden
    4.59
    hidden
    3.89
     gem
    3.63
     gems
    3.53
     Hidden
    3.48
    Hidden
    3.36
    HIDDEN
    2.78
     treasures
    2.63
    gems
    2.56
     Gems
    2.53
    Activations Density 0.039%

    No Known Activations