© 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. 84356
    Prev
    Next
    INDEX
    Explanations

    control characters and technical explanations

    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
    ing
    0.50
     registering
    0.47
    modelLogin
    0.46
    ة
    0.46
    百万
    0.45
    ampler
    0.45
    ಲು
    0.44
    國
    0.44
    大型
    0.44
     solicited
    0.44
    POSITIVE LOGITS
    chiha
    0.55
     조
    0.48
     є
    0.48
     영
    0.47
     выбора
    0.46
     형
    0.45
    ificant
    0.45
    0.45
     사용하는
    0.44
     היה
    0.43
    Activations Density 0.000%

    No Known Activations