© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1393
    Prev
    Next
    INDEX
    Explanations

    object that is free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ↵↵
    0.90
     constantly
    0.84
     through
    0.81
     combating
    0.81
     upon
    0.80
     over
    0.76
     clever
    0.75
     makers
    0.74
     tender
    0.73
     gains
    0.73
    POSITIVE LOGITS
     çift
    0.97
     edhe
    0.96
     testTakePhoto
    0.93
     doubleheader
    0.93
     nedenle
    0.92
    鷳
    0.91
    𒄫
    0.90
    <unused2080>
    0.90
    𒀤
    0.90
    ﺭ
    0.90
    Activations Density 0.000%

    No Known Activations