© 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. 1215
    Prev
    Next
    INDEX
    Explanations

    abstract concepts introducing details

    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
    м
    1.22
    scapes
    1.22
    чик
    1.00
    ਕ
    0.98
    𝒔
    0.98
    telegram
    0.97
    scape
    0.95
     soothe
    0.95
     fumble
    0.95
    𝙉
    0.94
    POSITIVE LOGITS
    ે
    1.27
    ات
    1.20
    ت
    1.20
    ের
    1.18
    र
    1.16
    is
    1.10
    ים
    1.09
    ার
    1.08
    ς
    1.08
    er
    1.04
    Activations Density 0.555%

    No Known Activations