© 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. 558
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
     if
    -2.05
    ではある
    -1.98
     nine
    -1.98
     CALIFORN
    -1.95
     while
    -1.91
    šné
    -1.84
     DEPOSITORY
    -1.83
    }$
    -1.83
     atendido
    -1.78
     which
    -1.76
    POSITIVE LOGITS
    背后
    2.08
     (…)
    1.94
    \
    1.91
    '
    1.87
     andare
    1.86
    </tfoot>
    1.86
    n
    1.84
    佧
    1.84
    —
    1.84
     rempliss
    1.83
    Activations Density 0.030%

    No Known Activations