© 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. 71695
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by punctuation

    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
    malte
    -0.97
     eerste
    -0.95
     första
    -0.94
    最初の
    -0.91
    Ừ
    -0.89
     একটি
    -0.88
     એ
    -0.87
    ksi
    -0.86
    ogues
    -0.86
     einer
    -0.85
    POSITIVE LOGITS
     what
    1.16
     that
    1.11
    phus
    0.95
    ();
    0.95
     how
    0.94
    habited
    0.93
     from
    0.90
    fiée
    0.89
    Распо
    0.88
    ㈣
    0.87
    Activations Density 0.040%

    No Known Activations