© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8416
    Prev
    Next
    INDEX
    Explanations

    wikipedia or Academy

    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_31_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
     подска
    0.53
    ดำ
    0.53
    chner
    0.51
    Maze
    0.51
    vänd
    0.51
    चर
    0.50
    ⥤
    0.50
     necessários
    0.50
     javac
    0.50
    Input
    0.50
    POSITIVE LOGITS
     സമൂ
    0.69
     степени
    0.61
    ሱን
    0.61
     믿
    0.60
    ल्पनिक
    0.58
    믿
    0.58
    commonly
    0.57
    诿
    0.57
     పోటీ
    0.55
    esc
    0.54
    Activations Density 0.037%

    No Known Activations