© 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-65K
    7. 181
    Prev
    Next
    INDEX
    Explanations

    website domain /

    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_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
    కు
    0.61
     Byl
    0.55
    是
    0.53
    }=
    0.49
    }];
    0.49
    因為
    0.48
    ALA
    0.48
    이지만
    0.48
    只限
    0.47
     Confucian
    0.47
    POSITIVE LOGITS
    com
    0.72
    t
    0.61
     tubuh
    0.59
     can
    0.57
    can
    0.57
     comet
    0.57
    et
    0.56
    ृत
    0.55
    c
    0.55
     from
    0.54
    Activations Density 0.117%

    No Known Activations