© 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. 22-GEMMASCOPE-RES-131K
    7. 73267
    Prev
    Next
    INDEX
    Explanations

    places and publications

    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_22/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
     perform
    -1.02
    bermuda
    -0.98
     to
    -0.98
     also
    -0.97
    影视
    -0.94
    입니다
    -0.94
    ませんが
    -0.93
    今後の
    -0.93
    ...@
    -0.92
     procedure
    -0.91
    POSITIVE LOGITS
    issez
    1.08
    𝗥
    1.00
    ⁇
    0.98
    weiter
    0.98
     säs
    0.96
    hmm
    0.95
    Hudson
    0.94
    癀
    0.94
     ögon
    0.94
    forder
    0.94
    Activations Density 0.005%

    No Known Activations