© 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. 41274
    Prev
    Next
    INDEX
    Explanations

    statistical inference

    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
    t
    0.53
    River
    0.53
     সভায়
    0.50
    ካት
    0.50
    Rivers
    0.48
    SC
    0.47
    odel
    0.46
    tion
    0.46
    ンスター
    0.46
    でした
    0.46
    POSITIVE LOGITS
    ي
    0.60
    ك
    0.58
     tengan
    0.57
     compuestos
    0.57
     milhares
    0.56
    ి
    0.55
     spät
    0.55
     الض
    0.55
     служи
    0.54
     pubblica
    0.53
    Activations Density 0.001%

    No Known Activations