© 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. 40304
    Prev
    Next
    INDEX
    Explanations

    bypassing safety filters

    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
     cle
    0.42
    க்களை
    0.42
     \$
    0.41
    ից
    0.41
     אין
    0.41
     cellulosic
    0.41
     กว่า
    0.41
     Yas
    0.40
     ethan
    0.40
     вле
    0.39
    POSITIVE LOGITS
    思った
    0.48
    擊
    0.43
    প্
    0.42
    ^+,
    0.41
    触
    0.41
    थित
    0.41
    nymi
    0.40
    ,"+
    0.40
    opoulos
    0.39
    utus
    0.39
    Activations Density 0.050%

    No Known Activations