© 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. 5802
    Prev
    Next
    INDEX
    Explanations

    importance, necessity, difficulty

    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
     whiche
    0.28
     auxqu
    0.27
     analyzers
    0.27
     које
    0.27
     filaments
    0.26
     («
    0.25
    (
    0.25
    ම්
    0.25
    는데
    0.25
     combing
    0.25
    POSITIVE LOGITS
     de
    0.34
    ate
    0.30
    ne
    0.30
    pping
    0.29
     clearly
    0.29
    on
    0.28
     difficult
    0.27
     aware
    0.27
     d
    0.27
     argued
    0.26
    Activations Density 0.261%

    No Known Activations