© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    numbered or lettered points

    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
    tion
    1.97
    े
    1.67
    tions
    1.56
     причем
    1.50
    tract
    1.49
    eyeglasses
    1.49
    skull
    1.48
    dog
    1.47
    𝖙
    1.45
     conical
    1.45
    POSITIVE LOGITS
     lediglich
    1.66
    ן
    1.51
    ર
    1.49
    hatian
    1.38
     IA
    1.36
     fhe
    1.36
    S
    1.35
    ementara
    1.34
    ন্যাশনাল
    1.32
    र
    1.31
    Activations Density 0.212%

    No Known Activations