© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13637
    Prev
    Next
    INDEX
    Explanations

    best for suitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \
    0.98
    You
    0.86
    The
    0.84
    '
    0.81
    ’
    0.80
    ר
    0.79
    т
    0.79
    Z
    0.79
    We
    0.78
    De
    0.78
    POSITIVE LOGITS
    ния
    0.79
     suited
    0.77
    immung
    0.77
    iaire
    0.75
    codigo
    0.72
    in
    0.70
    iality
    0.68
     बेस्ट
    0.67
    ುಕ
    0.66
    suited
    0.66
    Activations Density 0.069%

    No Known Activations