© 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. 41906
    Prev
    Next
    INDEX
    Explanations

    dividing or slideshow

    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
     При
    0.82
     ques
    0.82
    する
    0.81
     despise
    0.80
    Ⴎ
    0.80
     пусты
    0.80
     perforated
    0.79
     WPS
    0.79
     ү
    0.78
     Alic
    0.78
    POSITIVE LOGITS
    dengan
    0.76
    eye
    0.75
    бля
    0.71
     accanto
    0.70
     efficacement
    0.66
    讫
    0.65
    linson
    0.63
     morceaux
    0.63
    effective
    0.63
    ylated
    0.63
    Activations Density 0.000%

    No Known Activations