© 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. 204751
    Prev
    Next
    INDEX
    Explanations

    phrase completion

    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
     vapour
    0.46
     pubescent
    0.44
    掝
    0.44
     बढ़ने
    0.43
     снять
    0.42
    ड़क
    0.42
     ایش
    0.42
     पढ़ें
    0.42
     splendour
    0.42
    ậm
    0.41
    POSITIVE LOGITS
    en
    0.61
    ed
    0.57
    et
    0.54
    മല്ല
    0.52
    bet
    0.49
    i
    0.48
    al
    0.48
    edt
    0.48
     bestimmte
    0.47
    পো
    0.47
    Activations Density 0.001%

    No Known Activations