© 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. 198184
    Prev
    Next
    INDEX
    Explanations

    tied scores

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

    tied up or tied with

    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
    ى
    0.50
     thinner
    0.50
     receding
    0.50
     entretenimiento
    0.49
     converters
    0.49
     crevices
    0.47
     fissure
    0.46
     smaller
    0.46
     cameras
    0.46
    缪
    0.46
    POSITIVE LOGITS
    绑
    0.71
    綁
    0.64
     tying
    0.60
     tied
    0.60
     Tied
    0.59
    Tie
    0.57
    knot
    0.56
     Tie
    0.55
    tied
    0.53
    を結
    0.51
    Activations Density 0.023%

    No Known Activations