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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109273
    Prev
    Next
    INDEX
    Explanations

    comparing differences and needs

    np_acts-logits-general · gemini-2.5-flash-lite

    training programs, treatment, grappling with, significant changes, horizontal stack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    囱
    0.45
     इनमें
    0.44
    润
    0.44
     embl
    0.43
    建
    0.43
    这些
    0.42
     aussi
    0.42
    这个
    0.42
     caut
    0.41
    生
    0.41
    POSITIVE LOGITS
     आक्रोश
    0.47
     సమస్య
    0.47
     problema
    0.47
     почув
    0.46
     coronavirus
    0.45
     accusations
    0.45
     なさい
    0.44
    itabbam
    0.44
     baseless
    0.44
     پیروی
    0.43
    Activations Density 0.001%

    No Known Activations