© 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-65K
    7. 40462
    Prev
    Next
    INDEX
    Explanations

    refers to, resistance is, lie is, import all

    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_65k_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
     사람들이
    0.48
    枤
    0.46
     mutta
    0.46
     হঠাৎ
    0.43
     গবেষণ
    0.43
    ukiyoe
    0.43
    hombre
    0.43
    ピアノ
    0.42
    疹
    0.42
    但我
    0.42
    POSITIVE LOGITS
     २०२
    0.47
     ২০২৩
    0.46
     Metaverse
    0.46
     ২০২২
    0.45
     Kaspersky
    0.45
     YouTuber
    0.45
     Optionen
    0.45
     את
    0.44
     ئەو
    0.43
     Login
    0.43
    Activations Density 0.001%

    No Known Activations