© 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-262K
    7. 79590
    Prev
    Next
    INDEX
    Explanations

    how I would

    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
    帛
    0.49
     வலிய
    0.48
     Dutton
    0.45
     Hickory
    0.45
    versch
    0.45
    AKT
    0.45
    هرات
    0.44
     فوټبال
    0.44
     Colton
    0.44
     Warrington
    0.44
    POSITIVE LOGITS
     adherence
    0.49
     disdain
    0.49
     características
    0.48
     discriminatory
    0.46
     minute
    0.42
    ł
    0.42
    ก
    0.41
     regularity
    0.41
     parable
    0.40
    ified
    0.40
    Activations Density 0.001%

    No Known Activations