© 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. 93813
    Prev
    Next
    INDEX
    Explanations

    Platonic solids and specific relationships

    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
     איך
    0.53
    Ꮪ
    0.50
     אנחנו
    0.48
    经济
    0.47
    tevõ
    0.47
    ՞
    0.46
    ুম
    0.46
    ającym
    0.46
    勖
    0.46
     무엇
    0.45
    POSITIVE LOGITS
     unless
    0.52
     except
    0.50
     fraction
    0.49
     clears
    0.46
     subtlety
    0.46
     subclass
    0.46
     fractional
    0.45
     overall
    0.45
     evaluated
    0.45
     unsaturated
    0.43
    Activations Density 0.017%

    No Known Activations