© 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. 10-GEMMASCOPE-RES-131K
    4. 689
    Prev
    Next
    INDEX
    Explanations

    stock market trades

    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_10/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
    ⟣
    -1.91
    𖣔
    -1.66
     menjadi
    -1.66
     salão
    -1.60
    новь
    -1.60
    samt
    -1.59
    ꙰
    -1.56
     Bemerkungen
    -1.55
     nuestros
    -1.54
     Betrach
    -1.54
    POSITIVE LOGITS
     those
    1.83
    B
    1.75
    }
    1.63
    that
    1.53
     that
    1.48
    专用
    1.44
    :……
    1.41
     That
    1.39
     by
    1.38
    ệu
    1.38
    Activations Density 0.001%

    No Known Activations