© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106600
    Prev
    Next
    INDEX
    Explanations

    rarely perfect or predictable

    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_16_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
    ﻟ
    1.14
    ۰
    0.89
     ส
    0.87
     ร
    0.86
    л
    0.86
     נ
    0.80
     น้ำ
    0.79
     ล
    0.79
    ﻠ
    0.79
     feito
    0.78
    POSITIVE LOGITS
    س
    1.24
    ش
    1.08
    ેશ
    1.06
    ە
    1.04
    re
    1.00
    es
    1.00
    ين
    0.99
    ار
    0.98
    ="
    0.97
    وس
    0.97
    Activations Density 0.003%

    No Known Activations