© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43210
    Prev
    Next
    INDEX
    Explanations

    description of Scratch

    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
    n
    1.02
     Nisha
    0.96
     ourselves
    0.93
     beset
    0.89
     Muit
    0.88
     Height
    0.86
    挕
    0.86
    th
    0.84
     Eng
    0.84
    ہ
    0.84
    POSITIVE LOGITS
     globe
    0.71
    מר
    0.63
    Yahoo
    0.63
    Oro
    0.62
    funcs
    0.62
    hungry
    0.61
    Loire
    0.61
    妆
    0.60
     fame
    0.59
    מור
    0.59
    Activations Density 0.000%

    No Known Activations