© 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. 69085
    Prev
    Next
    INDEX
    Explanations

    Marine Air or The View

    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
    carus
    -0.86
    다고
    -0.83
     MUM
    -0.83
    ACHUSETTS
    -0.82
    unno
    -0.82
    アルミ
    -0.81
     ブラウン
    -0.81
     degli
    -0.81
    ئی
    -0.79
     ordenador
    -0.79
    POSITIVE LOGITS
    tentu
    0.91
    baca
    0.91
     complicada
    0.90
     torebka
    0.88
     their
    0.84
     lagt
    0.84
     seguimos
    0.83
     яйцо
    0.82
     zaji
    0.82
     modalidades
    0.81
    Activations Density 0.025%

    No Known Activations