© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138138
    Prev
    Next
    INDEX
    Explanations

    Key changes and why

    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
     tar
    0.47
     손
    0.46
     coral
    0.45
     او
    0.45
     교육
    0.44
     petróleo
    0.44
    rectomy
    0.44
     pea
    0.42
     customtkinter
    0.42
     որ
    0.41
    POSITIVE LOGITS
    Type
    0.50
    Cher
    0.50
    a
    0.49
    É
    0.47
    『
    0.46
    త్
    0.46
    Dreams
    0.44
    缃
    0.44
    TypeScript
    0.44
    È
    0.44
    Activations Density 0.006%

    No Known Activations