© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    Dieter said

    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
     bitmap
    0.62
    while
    0.58
    recursive
    0.58
    fashioned
    0.56
     cellulose
    0.56
     congestion
    0.56
    provider
    0.55
    ే
    0.55
    stricken
    0.54
    நிலைய
    0.54
    POSITIVE LOGITS
     ने
    0.67
     были
    0.67
     يريد
    0.66
     أن
    0.66
     كان
    0.65
     ي
    0.64
     был
    0.63
     способен
    0.62
    たちは
    0.61
     сможет
    0.61
    Activations Density 0.006%

    No Known Activations