© 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. 15914
    Prev
    Next
    INDEX
    Explanations

    specific strengths humor story

    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
     효
    0.45
     જો
    0.45
    ת
    0.43
     їх
    0.41
    적인
    0.41
     మే
    0.41
    辐射
    0.41
     제시
    0.41
     இடம்
    0.41
    ↵
    0.40
    POSITIVE LOGITS
    oló
    0.47
     aki
    0.43
     Humor
    0.42
     &,
    0.42
     cunoscut
    0.42
     humor
    0.41
    :
    0.41
     Storia
    0.41
     avait
    0.40
     attachments
    0.40
    Activations Density 0.001%

    No Known Activations