© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49412
    Prev
    Next
    INDEX
    Explanations

    close communication, contact, partnership

    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
     (
    0.58
    ى
    0.57
    s
    0.56
    </table>
    0.55
    ’
    0.53
    liğini
    0.53
    ’,
    0.52
    )’
    0.52
    )}_{
    0.50
    كة
    0.49
    POSITIVE LOGITS
     closed
    0.90
     closure
    0.87
     fermé
    0.86
     clos
    0.86
     close
    0.80
    封闭
    0.80
     fermeture
    0.79
     chiuso
    0.77
    close
    0.74
     closeup
    0.74
    Activations Density 0.038%

    No Known Activations