© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11470
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

    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
     embaraz
    -1.44
     and
    -1.41
    に来て
    -1.35
    なのが
    -1.35
    不
    -1.34
    に来
    -1.34
    に行った
    -1.32
     betek
    -1.31
     mengatasi
    -1.30
    ちゃんは
    -1.30
    POSITIVE LOGITS
    を
    1.65
    但在
    1.50
     in
    1.48
    但却
    1.42
    ですが
    1.42
    が
    1.39
    方針
    1.35
    但是在
    1.35
     can
    1.34
    態度
    1.31
    Activations Density 0.022%

    No Known Activations