© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148506
    Prev
    Next
    INDEX
    Explanations

    places and raw urls

    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_29_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
    postas
    0.81
     CNC
    0.78
     princípios
    0.77
    cnc
    0.76
     Numero
    0.76
    ﺅ
    0.74
     المت
    0.74
    Integrante
    0.74
    aleza
    0.72
     регі
    0.70
    POSITIVE LOGITS
    AnimationStyle
    0.69
    Dataset
    0.69
    怡
    0.68
    Bir
    0.68
    ドラマ
    0.68
     dataset
    0.66
    安
    0.65
    eb
    0.63
    nah
    0.61
    dataFile
    0.61
    Activations Density 0.002%

    No Known Activations