© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 31852
    Prev
    Next
    INDEX
    Explanations

    fan favorite, other otherwise

    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
     ﺍﻟ
    0.73
     ﺍ
    0.71
     necessario
    0.69
     unul
    0.67
    jarige
    0.67
     त्यामुळे
    0.66
    .=
    0.63
    .!
    0.61
     थी
    0.60
    Jangan
    0.60
    POSITIVE LOGITS
    ↵↵
    0.72
    ת
    0.69
    </h3>
    0.64
    },
    0.58
    ку
    0.58
    ся
    0.57
    روش
    0.57
    تمل
    0.56
    大
    0.55
    科技
    0.55
    Activations Density 0.000%

    No Known Activations