© 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. 66077
    Prev
    Next
    INDEX
    Explanations

    impressive positive descriptions

    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
     with
    -2.09
     in
    -2.08
     if
    -2.05
     at
    -1.91
     bæ
    -1.80
    ？？
    -1.74
    ❗
    -1.70
    🤑
    -1.70
     when
    -1.67
    😈
    -1.65
    POSITIVE LOGITS
     amd
    2.05
     overarching
    2.05
     gigantic
    2.03
     magnificent
    2.02
     lauded
    1.98
     wonderfully
    1.97
     tremendous
    1.96
     wonderful
    1.95
     insanely
    1.95
     insane
    1.94
    Activations Density 0.046%

    No Known Activations