© 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. 3765
    Prev
    Next
    INDEX
    Explanations

    numbers and questions

    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
     &/
    2.91
     mutlaka
    2.80
    或是
    2.67
     commentaries
    2.51
     souvent
    2.50
     ofta
    2.48
     voire
    2.45
     bölges
    2.43
     resalt
    2.40
     nuanced
    2.40
    POSITIVE LOGITS
     randomly
    0.85
     four
    0.80
    5
    0.79
    7
    0.78
     thirteen
    0.77
    8
    0.75
    6
    0.74
     thirty
    0.74
     six
    0.73
    eight
    0.73
    Activations Density 1.448%

    No Known Activations