© 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. 57805
    Prev
    Next
    INDEX
    Explanations

    forward, pass, share, give

    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
    glGen
    -0.71
    曝光
    -0.70
    álise
    -0.70
     MemoryStream
    -0.69
    amblea
    -0.69
    qrst
    -0.68
     ingress
    -0.67
     Respiratory
    -0.67
    rischen
    -0.66
     Hormone
    -0.66
    POSITIVE LOGITS
     passed
    3.72
     pass
    3.69
     passing
    3.66
     passes
    3.28
     переда
    3.19
    pass
    3.09
     Passing
    3.00
    Passing
    2.98
    Pass
    2.92
    passed
    2.89
    Activations Density 0.051%

    No Known Activations