© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138295
    Prev
    Next
    INDEX
    Explanations

    Rebellion, protests, verbatim, Chamberlain

    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_16_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
    are
    0.81
    ح
    0.80
    able
    0.67
    asas
    0.66
    ل
    0.66
    و
    0.66
    ،
    0.65
     nuovi
    0.63
    itude
    0.62
    ความ
    0.62
    POSITIVE LOGITS
     था
    0.54
     थी
    0.51
     దీ
    0.51
    కు
    0.51
    ↵↵
    0.50
     ద
    0.50
     ụ
    0.49
    \
    0.49
     ké
    0.49
    бек
    0.49
    Activations Density 0.001%

    No Known Activations