© 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-262K
    7. 11030
    Prev
    Next
    INDEX
    Explanations

    unique solution or each unit

    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_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
     respite
    1.14
    ذا
    1.13
     contatto
    1.08
    ة
    1.07
    在
    1.07
     ru
    1.04
     tension
    1.04
     esa
    1.03
     él
    1.02
     packed
    1.02
    POSITIVE LOGITS
    c
    1.40
    риал
    1.34
    cartoon
    1.32
     видеть
    1.28
    Ш
    1.28
    SELL
    1.27
    ython
    1.24
    NRC
    1.24
    eyeglasses
    1.20
    erende
    1.19
    Activations Density 0.000%

    No Known Activations