© 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. 11702
    Prev
    Next
    INDEX
    Explanations

    incrementing loop variables

    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
    an
    1.30
     waveguides
    1.12
    ان
    1.05
     sulfides
    0.98
    ور
    0.96
    吗
    0.96
     thermocou
    0.95
    ა
    0.94
    ش
    0.93
    ка
    0.91
    POSITIVE LOGITS
    s
    1.30
     وعند
    1.02
    ς
    0.96
    𝗨
    0.95
    DEFGHIJKLMNOP
    0.94
    kings
    0.93
     l
    0.92
     j
    0.89
     n
    0.86
    north
    0.85
    Activations Density 0.000%

    No Known Activations