© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 40909
    Prev
    Next
    INDEX
    Explanations

    all (

    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
     Nodes
    0.95
    j
    0.93
    de
    0.92
    al
    0.89
     conocidos
    0.89
    rors
    0.87
    t
    0.87
    ي
    0.86
    ii
    0.85
     clubes
    0.85
    POSITIVE LOGITS
    里程
    0.74
     могло
    0.71
    }}^{*}\
    0.70
    都能
    0.69
     delinquent
    0.69
     amusement
    0.68
    ERK
    0.68
     ****",
    0.67
    ِ
    0.66
    蟀
    0.66
    Activations Density 0.000%

    No Known Activations