© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144322
    Prev
    Next
    INDEX
    Explanations

    AT cut, ROC Curve

    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
    ül
    0.49
    en
    0.46
    ਮ
    0.46
    竈
    0.44
    房子
    0.43
     utilizzo
    0.43
    ’
    0.43
     ইপিআর
    0.42
    }))$
    0.42
    pan
    0.42
    POSITIVE LOGITS
     squarely
    0.58
     Soud
    0.49
     screened
    0.48
     .”
    0.48
     scegli
    0.47
     presumptive
    0.47
     pivotal
    0.47
     conspicuously
    0.46
     diversified
    0.46
     confidently
    0.46
    Activations Density 0.000%

    No Known Activations