© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15178
    Prev
    Next
    INDEX
    Explanations

    it to

    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
    หรือ
    0.36
     estando
    0.36
     wale
    0.36
     från
    0.34
    榃
    0.33
    ness
    0.33
    จาก
    0.32
     fasi
    0.32
    ך
    0.32
     eventuali
    0.32
    POSITIVE LOGITS
    ដើម្បី
    0.36
    ごとに
    0.32
     zodat
    0.32
    Читати
    0.32
    若干
    0.31
    υτό
    0.31
     successivement
    0.31
    ুতের
    0.31
    mediated
    0.30
    ເພື່ອ
    0.30
    Activations Density 0.050%

    No Known Activations