© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143017
    Prev
    Next
    INDEX
    Explanations

    replaces, amusement, older

    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
    ról
    0.53
    ýt
    0.52
    ndon
    0.50
    śa
    0.50
    Источник
    0.48
    czę
    0.48
    𝚌
    0.48
    с
    0.47
    órias
    0.47
    ആര്‍
    0.47
    POSITIVE LOGITS
     election
    0.49
     patients
    0.49
     ang
    0.48
     inputted
    0.47
     Toll
    0.45
     toll
    0.45
     elet
    0.45
     aina
    0.44
     inputs
    0.44
     eller
    0.43
    Activations Density 0.003%

    No Known Activations