© 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. 205294
    Prev
    Next
    INDEX
    Explanations

    hidden magical layers

    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
    anfaatkan
    0.50
     fract
    0.49
    𝗶
    0.48
    ೃಹ
    0.48
     ਤੁਹਾ
    0.47
    iž
    0.46
    rosion
    0.46
    𝗻
    0.46
     உலக
    0.46
     berkata
    0.46
    POSITIVE LOGITS
    Cad
    0.43
    Bienvenidos
    0.41
    CT
    0.41
    KA
    0.41
    Lev
    0.40
    4
    0.39
    الا
    0.39
    2
    0.39
    ↵
    0.38
    Met
    0.38
    Activations Density 0.002%

    No Known Activations