© 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. 27983
    Prev
    Next
    INDEX
    Explanations

    crime, theft, seeking

    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
     no
    0.42
     atra
    0.40
     C
    0.38
    G
    0.38
     a
    0.37
     two
    0.37
     Infine
    0.37
    ă
    0.37
    一直是
    0.37
    మెంట్
    0.36
    POSITIVE LOGITS
    谋
    0.43
    謀
    0.42
    犯罪
    0.40
    ﻢ
    0.40
    窃
    0.39
     കാണ
    0.38
    寻找
    0.38
     ยาก
    0.38
    偷
    0.37
    OptionPane
    0.37
    Activations Density 0.003%

    No Known Activations