© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 53935
    Prev
    Next
    INDEX
    Explanations

    in turn

    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
     Après
    -1.09
    AddTagHelper
    -1.08
     mismas
    -1.07
    mouseout
    -1.05
    Otherwise
    -1.03
    UREAU
    -1.03
    lementary
    -1.02
    λλ
    -1.00
    也会
    -0.99
    ACHUSET
    -0.96
    POSITIVE LOGITS
     wiederum
    1.63
     then
    1.18
    さらに
    1.11
    .......
    1.09
     schließlich
    1.06
     ....
    1.03
    ....
    1.02
    .....
    1.02
    ......
    0.99
    ........
    0.95
    Activations Density 0.045%

    No Known Activations