© 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. 31559
    Prev
    Next
    INDEX
    Explanations

    vacuum environment

    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
    5
    0.61
     and
    0.61
    ъ
    0.59
    0
    0.58
    マ
    0.58
    ill
    0.58
    æ
    0.57
    and
    0.56
    라고
    0.56
     affine
    0.56
    POSITIVE LOGITS
     justa
    0.57
    }')
    0.57
     эш
    0.56
    রিটি
    0.55
     là
    0.54
     najważ
    0.54
    чена
    0.53
    lN
    0.53
    gı
    0.52
    jira
    0.52
    Activations Density 0.003%

    No Known Activations