© 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. 56472
    Prev
    Next
    INDEX
    Explanations

    displaying text and data

    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
    *
    0.79
    บ
    0.61
     into
    0.59
    מו
    0.59
    <
    0.59
     différents
    0.57
    OT
    0.56
    ."
    0.54
    *}
    0.54
     extend
    0.54
    POSITIVE LOGITS
    afficher
    0.71
     Anzeige
    0.68
     sentenza
    0.66
     exibir
    0.64
     Anzeigen
    0.61
     Displays
    0.61
     wyświet
    0.57
    Displays
    0.57
     Pursuant
    0.56
    вање
    0.56
    Activations Density 0.064%

    No Known Activations