© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13886
    Prev
    Next
    INDEX
    Explanations

    break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    й
    2.59
    йки
    2.31
    ால்
    2.05
    в
    2.04
    べき
    1.92
    вни
    1.90
    ли
    1.83
    рда
    1.82
    fers
    1.82
    र
    1.74
    POSITIVE LOGITS
     tuổi
    2.24
     khổ
    2.20
     технику
    2.15
     pandemics
    2.13
    ाइम
    2.08
     setUser
    2.07
    裂
    2.04
    SHADER
    2.04
     מז
    2.02
     passwords
    2.01
    Activations Density 0.268%

    No Known Activations