© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    different, influences, heat, significant

    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_24_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
     unbeaten
    0.77
    Г
    0.72
    Пет
    0.71
    어
    0.70
    П
    0.69
    Ꮑ
    0.68
    В
    0.67
    映像
    0.67
    ওয়্যার
    0.66
     diabetic
    0.64
    POSITIVE LOGITS
    ción
    0.83
     sabía
    0.80
     podía
    0.77
    posición
    0.76
     получили
    0.76
     cambió
    0.75
     skorzyst
    0.75
    puede
    0.75
     fiebre
    0.73
     měla
    0.73
    Activations Density 0.000%

    No Known Activations