© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12593
    Prev
    Next
    INDEX
    Explanations

    agreement and correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     LPARAM
    0.63
    ुल
    0.59
     lateral
    0.59
    立马
    0.59
    佉
    0.58
     blatant
    0.57
     Longitudinal
    0.56
    힣
    0.56
     practical
    0.55
     standards
    0.55
    POSITIVE LOGITS
     correct
    3.72
    correct
    3.42
    Correct
    3.38
     Correct
    3.30
     CORRECT
    3.11
     correcto
    2.97
     correctly
    2.96
    正确
    2.90
     correcta
    2.76
     correto
    2.63
    Activations Density 0.163%

    No Known Activations