© 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-262K
    7. 76864
    Prev
    Next
    INDEX
    Explanations

    php code blocks

    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_262k_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
    幸运
    0.46
     analytics
    0.44
     excepciones
    0.43
     breach
    0.43
     athlete
    0.42
     החד
    0.42
    ޤ
    0.42
     ativos
    0.41
     Analytics
    0.41
     unjust
    0.41
    POSITIVE LOGITS
    些
    0.49
    spacePad
    0.46
    idiendo
    0.45
    $\--
    0.44
    assignmentItems
    0.44
    reservation
    0.44
    sklär
    0.43
    xsi
    0.42
    rna
    0.42
    nienie
    0.42
    Activations Density 0.003%

    No Known Activations