© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195042
    Prev
    Next
    INDEX
    Explanations

    points and dimensionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    owels
    0.42
     never
    0.42
     Never
    0.42
    ieden
    0.41
    говари
    0.39
    鯢
    0.39
    टामिन
    0.38
     обязательно
    0.38
     능
    0.38
    coco
    0.38
    POSITIVE LOGITS
    Size
    0.49
     dimensionless
    0.49
    width
    0.46
    size
    0.45
     size
    0.44
     scambio
    0.43
     width
    0.42
    SIZE
    0.41
    奥行
    0.40
     puntual
    0.40
    Activations Density 0.010%

    No Known Activations