© 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. 10975
    Prev
    Next
    INDEX
    Explanations

    interesting/fascinating descriptions

    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
    м
    1.20
    і
    1.19
    ième
    1.13
    𝐢
    1.13
    л
    1.05
    мб
    1.02
    いない
    1.00
    ле
    0.99
    情况
    0.99
    不久
    0.99
    POSITIVE LOGITS
    atic
    0.99
     जिसे
    0.98
    Од
    0.98
    কিন্তু
    0.97
    atomy
    0.96
    Så
    0.96
    俎
    0.96
     Darüber
    0.95
     ביותר
    0.95
    इसलिए
    0.95
    Activations Density 0.340%

    No Known Activations