© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1771
    Prev
    Next
    INDEX
    Explanations

    bile duct, voiceover

    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_9_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
     kolej
    1.34
    toLocaleString
    1.24
    isVisible
    1.22
    sf
    1.21
    т
    1.20
    quot
    1.19
    응
    1.18
    ઇ
    1.17
    ଷ
    1.16
    nike
    1.14
    POSITIVE LOGITS
    varage
    1.59
    erler
    1.54
    ر
    1.47
    ย
    1.44
     bref
    1.42
    ociation
    1.37
     Spaß
    1.37
    ᴘ
    1.35
    رک
    1.34
    abek
    1.34
    Activations Density 0.024%

    No Known Activations