© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 643
    Prev
    Next
    INDEX
    Explanations

    dear followed by names or titles

    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
    ৄ
    -2.91
    ឣ
    -2.72
    聍
    -2.66
    揶
    -2.55
     untill
    -2.44
    ஂ
    -2.41
     neun
    -2.41
    拶
    -2.39
    ৢ
    -2.39
    )$
    -2.31
    POSITIVE LOGITS
    that
    3.34
    er
    3.19
    s
    2.80
    .
    2.63
    or
    2.59
    9
    2.47
    ly
    2.45
    $
    2.42
     the
    2.42
    This
    2.41
    Activations Density 0.007%

    No Known Activations