© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    direction or reversal

    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
    ochial
    0.44
    Meta
    0.42
    ⌒
    0.41
    uckle
    0.41
    兽
    0.40
    eryllium
    0.40
    ب
    0.40
    Cow
    0.40
    ণ
    0.39
    𒀀
    0.39
    POSITIVE LOGITS
     outfit
    0.49
     outfits
    0.47
     ergän
    0.47
     này
    0.46
     этого
    0.46
     konst
    0.44
     distal
    0.44
     từ
    0.43
     entrees
    0.43
     pakaian
    0.42
    Activations Density 0.011%

    No Known Activations