© 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. 5170
    Prev
    Next
    INDEX
    Explanations

    argues that

    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
     ו
    0.75
     તથા
    0.69
     אבל
    0.68
     possibilidades
    0.68
     podrá
    0.67
     tendrás
    0.67
     higiene
    0.67
     hemos
    0.66
     কিংবা
    0.65
     vortices
    0.65
    POSITIVE LOGITS
     the
    0.94
    the
    0.90
    that
    0.76
     this
    0.71
    .
    0.69
    this
    0.68
    ্যন্তরীণ
    0.66
    it
    0.66
     thei
    0.66
    ila
    0.65
    Activations Density 0.000%

    No Known Activations