© 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. 15212
    Prev
    Next
    INDEX
    Explanations

    code documentation tags

    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
     aquarium
    0.47
     astrophysics
    0.47
     radiotherapy
    0.47
     Joule
    0.44
     Balmer
    0.44
     cytoplasm
    0.44
    ြ
    0.43
     Aquarium
    0.42
     hydraulics
    0.42
     alkyl
    0.41
    POSITIVE LOGITS
    cgi
    0.51
    ക്കുറിച്ച
    0.50
     必要
    0.47
    return
    0.46
    url
    0.46
    버
    0.45
    のは
    0.44
     तुम्ह
    0.42
     پیدا
    0.42
    ಎ
    0.42
    Activations Density 0.029%

    No Known Activations