© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4288
    Prev
    Next
    INDEX
    Explanations

    time durations and days

    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_31_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
    baik
    0.42
     básica
    0.41
    威力
    0.40
    拢
    0.40
     Joyce
    0.39
     සැල
    0.38
    聿
    0.37
    quick
    0.37
    defaults
    0.37
     महत्वा
    0.37
    POSITIVE LOGITS
     exacte
    0.48
     exact
    0.44
     shorter
    0.44
    ]，
    0.40
     matchup
    0.39
    Of
    0.38
     hours
    0.38
     durations
    0.37
     using
    0.37
     факти
    0.37
    Activations Density 0.002%

    No Known Activations