© 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. 36214
    Prev
    Next
    INDEX
    Explanations

    not quite looking

    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
    نا
    0.49
     xổ
    0.47
    ვ
    0.46
    مر
    0.43
    伲
    0.42
     仮
    0.42
     integra
    0.41
    UER
    0.41
     statute
    0.41
     pern
    0.41
    POSITIVE LOGITS
    ():
    0.45
    ):
    0.43
     प्रतीत
    0.42
    ost
    0.42
    ogenic
    0.42
    ra
    0.40
    colors
    0.40
    red
    0.39
    else
    0.39
    continue
    0.39
    Activations Density 0.000%

    No Known Activations