© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    people or items go missing

    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
     струк
    0.43
     améli
    0.42
     ovlád
    0.42
     semantic
    0.42
     définir
    0.42
     концеп
    0.41
    Х
    0.41
    斜
    0.40
    观点
    0.39
     powert
    0.39
    POSITIVE LOGITS
     kidnapping
    0.82
     kidn
    0.77
     kidnapped
    0.76
     kidnap
    0.71
     abduction
    0.70
     rescue
    0.70
     abducted
    0.68
     लापता
    0.68
     missing
    0.68
    rescue
    0.67
    Activations Density 0.087%

    No Known Activations