© 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. 55579
    Prev
    Next
    INDEX
    Explanations

    very young

    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
    iče
    0.46
    ifferentiating
    0.45
     repair
    0.44
     Flow
    0.43
    <0x0D>
    0.43
    headed
    0.43
     persamaan
    0.43
     flows
    0.42
     Flows
    0.42
    ónica
    0.42
    POSITIVE LOGITS
    كل
    0.56
    كم
    0.52
    ם
    0.50
    ﻡ
    0.50
     כש
    0.47
    وین
    0.45
    តម្លៃ
    0.44
    ۰۰
    0.44
     Стаўкі
    0.43
     ahuv
    0.43
    Activations Density 0.003%

    No Known Activations