© 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. 108408
    Prev
    Next
    INDEX
    Explanations

    very special

    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
    ズ
    0.47
    க்கு
    0.46
    如何在
    0.46
    শিশ
    0.45
     seduce
    0.45
    ють
    0.44
    ク
    0.44
     turno
    0.44
    ಲ್
    0.43
    ﻃ
    0.43
    POSITIVE LOGITS
    шкой
    0.50
     architect
    0.47
    atot
    0.46
     august
    0.45
     måste
    0.44
     ü
    0.43
     अंश
    0.43
    ingly
    0.43
    aren
    0.42
     angry
    0.42
    Activations Density 0.003%

    No Known Activations