© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 104973
    Prev
    Next
    INDEX
    Explanations

    hidden gem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    cznie
    0.63
    ہ
    0.59
    щую
    0.59
     الا
    0.57
    gars
    0.57
    zept
    0.54
    jeno
    0.54
    ール
    0.54
    нд
    0.54
    zigen
    0.53
    POSITIVE LOGITS
     faisait
    0.59
    ↵↵
    0.54
     dichas
    0.52
     transcriptome
    0.50
     mandibular
    0.50
     rid
    0.49
     halftime
    0.49
     recombination
    0.48
     eryth
    0.47
     sécr
    0.47
    Activations Density 0.000%

    No Known Activations