© 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. 108110
    Prev
    Next
    INDEX
    Explanations

    bible book names

    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
     emphasized
    0.48
     emphasizing
    0.48
     Paragraph
    0.46
    id
    0.45
    im
    0.44
     Emphasis
    0.44
     Index
    0.43
     ဟ
    0.43
     In
    0.43
     emphasizes
    0.42
    POSITIVE LOGITS
     sním
    0.51
     personnalisé
    0.49
     ricos
    0.48
     esperti
    0.46
    주일
    0.46
     girlfriend
    0.45
    CategoryImage
    0.44
    ﮏ
    0.44
     gamble
    0.44
     comorbidities
    0.44
    Activations Density 0.004%

    No Known Activations