© 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-65K
    7. 28474
    Prev
    Next
    INDEX
    Explanations

    access API

    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_65k_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
     کھانا
    0.46
     Bildschirm
    0.45
     음식
    0.44
    貘
    0.44
     食品
    0.43
     merchant
    0.43
    彌
    0.40
    0.40
     prést
    0.40
     agrícola
    0.40
    POSITIVE LOGITS
    ร
    0.47
    annis
    0.43
    arreg
    0.41
     MUST
    0.40
    噂
    0.40
    бели
    0.39
    বে
    0.39
     rigidly
    0.38
     रण
    0.38
    explicit
    0.38
    Activations Density 0.013%

    No Known Activations