© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    programming constructs and AI models

    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
    7
    0.70
     сегодня
    0.67
    6
    0.66
    bff
    0.63
     família
    0.63
    colorful
    0.62
     Freeman
    0.61
     escola
    0.61
     сьогодні
    0.59
    4
    0.58
    POSITIVE LOGITS
    November
    1.44
    December
    1.43
    <.
    1.43
    counted
    1.40
     December
    1.36
    μβρίου
    1.35
     November
    1.34
     deduction
    1.32
     ALG
    1.27
    ration
    1.27
    Activations Density 0.015%

    No Known Activations