© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11969
    Prev
    Next
    INDEX
    Explanations

    subtracting the value

    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_31_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
     ympä
    0.43
    Bitmap
    0.43
    ම්
    0.42
     tä
    0.41
     agric
    0.41
     cinematography
    0.40
    鎗
    0.40
     आपण
    0.39
     Bioinformatics
    0.39
     Ambiental
    0.39
    POSITIVE LOGITS
    t
    0.53
    subtract
    0.50
    자를
    0.46
     रोग
    0.45
    僌
    0.42
    那些
    0.42
     enfe
    0.41
     верну
    0.41
     ಜೊ
    0.41
    tive
    0.41
    Activations Density 0.007%

    No Known Activations