© 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. 36267
    Prev
    Next
    INDEX
    Explanations

    tech platforms and proper nouns

    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
     illustrate
    -1.58
     those
    -1.52
     also
    -1.39
    ~。
    -1.38
    şık
    -1.38
    を見る
    -1.35
    zczy
    -1.34
    鄜
    -1.31
    ili
    -1.31
     straips
    -1.30
    POSITIVE LOGITS
    咄
    1.59
    ейчас
    1.58
    Externí
    1.46
     diskusi
    1.45
    白衣
    1.45
    了她
    1.41
     negli
    1.41
     are
    1.38
     '~
    1.38
    leiding
    1.37
    Activations Density 0.226%

    No Known Activations