© 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. 619
    Prev
    Next
    INDEX
    Explanations

    in place of

    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
     on
    -2.33
    .
    -2.30
     nahezu
    -1.85
     despite
    -1.65
     unparalleled
    -1.64
     erheb
    -1.64
     unangemess
    -1.59
     September
    -1.51
     at
    -1.51
    érables
    -1.49
    POSITIVE LOGITS
     ส์
    2.33
    ↵
    2.09
    </sub>
    2.05
    ah
    2.00
    譟
    1.86
    aw
    1.84
    ach
    1.81
    aaaa
    1.79
    a
    1.78
     zoude
    1.77
    Activations Density 0.008%

    No Known Activations