© 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-16K
    7. 1400
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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_16k_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
     Hol
    0.71
    蠢
    0.69
    ró
    0.61
     Ack
    0.60
     Rap
    0.60
    ids
    0.59
    赖
    0.57
    ieux
    0.56
    jaa
    0.56
     jigs
    0.56
    POSITIVE LOGITS
    }°
    1.61
     Configur
    1.54
     Fernanda
    1.52
    Export
    1.52
     ProductCategory
    1.49
     BSTC
    1.49
     Heater
    1.49
     Quillen
    1.48
     Export
    1.47
     Converting
    1.47
    Activations Density 0.148%

    No Known Activations