© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45637
    Prev
    Next
    INDEX
    Explanations

    code syntax, file paths, structures

    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_34/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
    collectionView
    -0.84
    skog
    -0.84
    ведения
    -0.83
    abha
    -0.81
    MARGIN
    -0.79
    itosti
    -0.78
    [{{
    -0.77
    brook
    -0.77
    ->$
    -0.76
    Ṣ
    -0.76
    POSITIVE LOGITS
    displaystyle
    0.96
     display
    0.93
    DISP
    0.82
    fres
    0.80
     condemns
    0.79
     affichés
    0.79
     ofrecen
    0.78
     présentes
    0.76
    träglich
    0.75
     pollut
    0.74
    Activations Density 0.001%

    No Known Activations