© 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. 43497
    Prev
    Next
    INDEX
    Explanations

    tikz, latex formatting

    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
     manuscript
    0.50
    }$.
    0.43
     manuscripts
    0.42
    лини
    0.42
    assuming
    0.42
     supon
    0.42
    ⑭
    0.41
    欄
    0.41
    пси
    0.41
    த்தில்
    0.41
    POSITIVE LOGITS
     emoji
    0.45
     emojis
    0.45
     Yelp
    0.43
     Emoji
    0.42
     AK
    0.41
     y
    0.40
     Village
    0.40
     selfies
    0.40
    retching
    0.39
    resolver
    0.38
    Activations Density 0.000%

    No Known Activations