© 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. 28260
    Prev
    Next
    INDEX
    Explanations

    within or insertion

    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
    0
    0.59
     çö
    0.50
    皇家
    0.47
    ၽ
    0.46
     Motorcycles
    0.44
     noroeste
    0.44
     đứa
    0.44
    𝟬
    0.43
     দ্য
    0.41
     μεγάλη
    0.41
    POSITIVE LOGITS
     inputs
    0.67
    输入
    0.59
    setInput
    0.58
     internalType
    0.56
    以内
    0.56
    入力
    0.56
     getInput
    0.55
     dimas
    0.54
    inputs
    0.53
     insertion
    0.53
    Activations Density 0.034%

    No Known Activations