© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    Frontend related commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    3
    1.67
     mg
    1.60
    5
    1.56
    2
    1.55
    °
    1.54
    Data
    1.52
     wal
    1.44
    mg
    1.44
    6
    1.42
    7
    1.42
    POSITIVE LOGITS
     fråga
    1.70
     ẹ
    1.69
    AGUE
    1.63
    óny
    1.59
     lógico
    1.57
    gados
    1.52
    高志森
    1.50
     afectan
    1.48
    alho
    1.48
    ungannya
    1.47
    Activations Density 0.000%

    No Known Activations