© 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. 89208
    Prev
    Next
    INDEX
    Explanations

    guessing who or what

    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
    ي
    1.07
    ר
    0.94
    р
    0.79
    i
    0.75
    י
    0.75
     gamble
    0.74
    ر
    0.73
    ে
    0.67
    ك
    0.67
    ி
    0.66
    POSITIVE LOGITS
    have
    0.64
    ING
    0.61
    aft
    0.59
    ope
    0.57
    icas
    0.55
    onic
    0.55
    ↵
    0.55
    Have
    0.55
    imetric
    0.55
    alena
    0.55
    Activations Density 0.000%

    No Known Activations