© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 120106
    Prev
    Next
    INDEX
    Explanations

    common words and 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_40_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
     pim
    0.40
    N
    0.39
     entferne
    0.37
     detects
    0.37
     origine
    0.35
    raving
    0.35
    SNS
    0.35
     entfernen
    0.35
    button
    0.34
     spin
    0.34
    POSITIVE LOGITS
    複雜
    0.43
     Stopped
    0.43
    सागर
    0.41
    కో
    0.41
     প্রশ্নে
    0.41
    䣰
    0.41
    ColumnKind
    0.41
     ပ
    0.40
     پیام
    0.40
     воздух
    0.40
    Activations Density 0.004%

    No Known Activations