© 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. 107051
    Prev
    Next
    INDEX
    Explanations

    NullReference or Exception

    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
    带来的
    -0.89
    oursquare
    -0.85
     reconoció
    -0.82
     blend
    -0.77
     Personalised
    -0.76
    endency
    -0.76
     suele
    -0.76
     juuri
    -0.75
     spesa
    -0.75
     mahdol
    -0.74
    POSITIVE LOGITS
    ather
    0.79
     gradu
    0.78
    iL
    0.77
    pasta
    0.76
     Lugar
    0.73
    Dict
    0.73
     DIAGRAM
    0.73
    化粧
    0.73
    Ticks
    0.73
    𝒐
    0.73
    Activations Density 0.016%

    No Known Activations