© 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. 31850
    Prev
    Next
    INDEX
    Explanations

    to verb

    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
    ARE
    0.70
    ンの
    0.64
     livelli
    0.63
     classificação
    0.63
    )!
    0.62
     permukaan
    0.61
    ê
    0.61
    𝒆
    0.60
    .)
    0.60
    à
    0.59
    POSITIVE LOGITS
    هي
    0.68
    জেলা
    0.63
    هلاك
    0.60
    ிறது
    0.58
    ింది
    0.57
    ுடைய
    0.57
    ისა
    0.57
     Alte
    0.56
     Möglich
    0.55
     Unis
    0.55
    Activations Density 0.004%

    No Known Activations