© 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. 19922
    Prev
    Next
    INDEX
    Explanations

    scenic views

    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
    на
    1.36
    ка
    1.15
    ви
    1.06
    ме
    0.98
    не
    0.96
    но
    0.94
    म
    0.88
    в
    0.88
    то
    0.86
    ਾ
    0.82
    POSITIVE LOGITS
    ld
    0.92
    al
    0.91
    van
    0.84
    ut
    0.84
    press
    0.82
    rl
    0.81
    fer
    0.81
    utt
    0.81
    ret
    0.80
    ori
    0.79
    Activations Density 0.002%

    No Known Activations