© 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. 48716
    Prev
    Next
    INDEX
    Explanations

    instantiating objects

    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
    TProtocol
    -0.85
     IERC
    -0.81
    着她
    -0.78
     jt
    -0.77
    getNombre
    -0.75
    entable
    -0.73
    heater
    -0.73
    водства
    -0.73
     Internationale
    -0.73
     wishes
    -0.72
    POSITIVE LOGITS
     Default
    1.02
     Simple
    1.00
     αυτό
    0.84
     when
    0.83
     basadas
    0.82
    pinephrine
    0.82
     implementations
    0.81
     plain
    0.81
    entile
    0.81
    Default
    0.79
    Activations Density 0.068%

    No Known Activations