© 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. 401
    Prev
    Next
    INDEX
    Explanations

    wow this

    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
    แค
    0.52
    ﹐
    0.49
    ujar
    0.49
    shr
    0.48
     แค
    0.48
    <unused1465>
    0.48
    <unused1747>
    0.47
    Depending
    0.47
    expec
    0.47
    䒷
    0.46
    POSITIVE LOGITS
    '
    0.74
    名は
    0.72
    ’
    0.70
     Ltd
    0.67
     speaks
    0.65
     writes
    0.65
     is
    0.65
     adlı
    0.64
     appears
    0.64
    さんの
    0.63
    Activations Density 2.512%

    No Known Activations