© 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. 26748
    Prev
    Next
    INDEX
    Explanations

    class, Medical, Angel

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

    technical or scientific text with specialized terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     kré
    -1.15
    DECREF
    -1.10
     stratég
    -1.09
    ıyorum
    -1.08
    leren
    -1.06
    Szer
    -1.02
     alábbi
    -1.02
    şim
    -1.02
     kateg
    -1.02
     aldri
    -0.98
    POSITIVE LOGITS
    y
    1.08
    ka
    1.04
     demselben
    0.98
    a
    0.98
     '
    0.98
    ils
    0.97
     that
    0.95
    u
    0.95
     otras
    0.94
    N
    0.94
    Activations Density 0.000%

    No Known Activations