© 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. 31-GEMMASCOPE-2-RES-262K
    7. 169981
    Prev
    Next
    INDEX
    Explanations

    explain complex concepts

    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_31_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
     venire
    0.49
    s
    0.49
    textrm
    0.47
     reach
    0.47
    reach
    0.44
    Laundry
    0.43
    Saudi
    0.43
    യ
    0.42
    instant
    0.42
     superior
    0.40
    POSITIVE LOGITS
    简单的
    0.48
     fanciful
    0.46
     cheats
    0.45
     Escal
    0.44
     الفعل
    0.43
     Cálculo
    0.43
    物体
    0.43
    ைத்
    0.42
     Fears
    0.42
     أنواع
    0.42
    Activations Density 0.003%

    No Known Activations