© 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. 30604
    Prev
    Next
    INDEX
    Explanations

    webcomic comic variations dump

    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
    setGeometry
    0.42
     insecurity
    0.38
    ាស់
    0.38
     instructions
    0.38
    പാട
    0.38
     एखाद्या
    0.38
     सुरक्षा
    0.37
    逡
    0.36
     странах
    0.36
    োহর
    0.36
    POSITIVE LOGITS
    Pe
    0.44
    jis
    0.42
     Gori
    0.41
    ذب
    0.41
     Numer
    0.40
     slog
    0.40
    이브
    0.39
    ⟹
    0.39
     Ellen
    0.39
    De
    0.38
    Activations Density 0.000%

    No Known Activations