© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    8
    1.00
    4
    0.92
    6
    0.91
    5
    0.88
    (
    0.87
    7
    0.82
    3
    0.79
    9
    0.74
    ８
    0.74
    =
    0.71
    POSITIVE LOGITS
    ש
    0.66
    و
    0.66
     nouvel
    0.62
    ك
    0.59
     hanging
    0.58
    ו
    0.58
    .,
    0.56
     pering
    0.55
     uniformed
    0.55
    ድን
    0.54
    Activations Density 0.095%

    No Known Activations