© 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. 53-GEMMASCOPE-2-RES-262K
    4. 65717
    Prev
    Next
    INDEX
    Explanations

    a safe assistant

    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_53_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
     Wex
    0.41
     FIL
    0.39
    剞
    0.38
     Filing
    0.38
    Fil
    0.37
    Vis
    0.36
    ===============
    0.36
     филь
    0.35
    वाहा
    0.35
     odit
    0.35
    POSITIVE LOGITS
    dream
    0.42
     꿈
    0.41
     game
    0.40
    game
    0.40
     attraction
    0.40
    achment
    0.39
     fantasy
    0.39
     imagined
    0.39
     fantastical
    0.39
     बिल्
    0.39
    Activations Density 0.006%

    No Known Activations