© 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. 10-GEMMASCOPE-RES-131K
    7. 113155
    Prev
    Next
    INDEX
    Explanations

    hexadecimal notations and memory addresses

    np_acts-logits-general · gemini-2.5-flash-lite

    the digit zero in technical, mathematical, or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    _
    -1.60
     in
    -1.56
     there
    -1.55
     it
    -1.51
     my
    -1.45
     during
    -1.44
     on
    -1.44
     when
    -1.40
     to
    -1.37
     as
    -1.34
    POSITIVE LOGITS
     kaos
    1.78
     kazak
    1.66
    YNAMICS
    1.61
     kader
    1.54
    ￦
    1.49
    Plusieurs
    1.49
     dezelve
    1.48
    sieger
    1.48
    ,—
    1.46
     samti
    1.46
    Activations Density 0.002%

    No Known Activations