© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35590
    Prev
    Next
    INDEX
    Explanations

    dice `d` followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     sở
    0.87
     Pea
    0.84
     âge
    0.78
     Provence
    0.77
    ​—
    0.77
     类型
    0.77
     ai
    0.75
     οι
    0.74
     aroused
    0.74
     horde
    0.73
    POSITIVE LOGITS
    ваются
    0.90
    ૧
    0.86
    itch
    0.80
    ton
    0.78
     देखकर
    0.76
     famílias
    0.75
    centos
    0.75
    𝘔
    0.75
    ेस
    0.74
    iça
    0.74
    Activations Density 0.000%

    No Known Activations