© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119503
    Prev
    Next
    INDEX
    Explanations

    vertical orientation

    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
    quis
    0.41
    하라
    0.39
    煤
    0.39
    anking
    0.38
    itures
    0.38
     జ
    0.37
     Markt
    0.37
     Fund
    0.37
    tvrt
    0.37
     attracts
    0.36
    POSITIVE LOGITS
    Symbols
    0.41
    extends
    0.39
    Merge
    0.38
    ']).
    0.38
    TypeList
    0.38
    Vertical
    0.38
    multiply
    0.38
    forever
    0.38
    Structure
    0.38
     microbiome
    0.37
    Activations Density 0.000%

    No Known Activations