© 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. 22-GEMMASCOPE-RES-131K
    7. 104710
    Prev
    Next
    INDEX
    Explanations

    Appellee/Appellant

    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
    pushFollow
    -0.88
    mtb
    -0.88
     élevés
    -0.87
     Risiko
    -0.87
     his
    -0.86
     ammat
    -0.85
    に入れ
    -0.84
    の地
    -0.84
     różnych
    -0.83
     présentes
    -0.83
    POSITIVE LOGITS
    って思
    0.91
    やろ
    0.90
    әне
    0.88
    ěla
    0.84
    接下来
    0.83
     quedará
    0.82
    ciech
    0.81
    esseur
    0.81
    ídos
    0.79
     wró
    0.79
    Activations Density 0.056%

    No Known Activations