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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204591
    Prev
    Next
    INDEX
    Explanations

    corporate, civic, or charitable boards

    np_acts-logits-general · gemini-2.5-flash-lite

    following introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Genre
    0.53
    ar
    0.49
    <0x8E>
    0.47
    genres
    0.45
    arr
    0.45
    ig
    0.45
    ug
    0.45
    -
    0.44
    пр
    0.44
    ri
    0.44
    POSITIVE LOGITS
     ವಿಷ
    0.57
     সৌম
    0.49
     இருக்கலாம்
    0.48
     تكون
    0.48
    marshalN
    0.48
     cambiado
    0.48
     रवा
    0.48
     PBA
    0.47
     consultations
    0.47
     ビジネス
    0.47
    Activations Density 0.000%

    No Known Activations