© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31107
    Prev
    Next
    INDEX
    Explanations

    eight

    np_acts-logits-general · gemini-2.5-flash-lite

    representations of eight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     społ
    0.43
     돼요
    0.38
    ैनिक
    0.37
    ία
    0.36
    Maritime
    0.36
    <unused15>
    0.35
     đị
    0.35
    ≋
    0.35
    ίες
    0.34
    seys
    0.34
    POSITIVE LOGITS
     ocho
    0.65
     आठ
    0.61
     oito
    0.59
     eight
    0.58
     восем
    0.57
     acht
    0.57
     Eight
    0.54
     eighties
    0.53
     আট
    0.53
    Eight
    0.52
    Activations Density 0.062%

    No Known Activations