© 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. 55465
    Prev
    Next
    INDEX
    Explanations

    "to" followed by a word

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

    don't have

    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
    শ
    0.52
     fluxes
    0.49
     activity
    0.46
     contrasts
    0.46
     reciproc
    0.45
     halide
    0.45
     bully
    0.44
     stated
    0.44
     flux
    0.44
     bullying
    0.44
    POSITIVE LOGITS
    桻
    0.50
    elist
    0.49
     पाना
    0.49
    ainer
    0.48
     अमर
    0.45
    êter
    0.45
    ému
    0.45
    侔
    0.44
     الأمير
    0.44
    ปลาย
    0.44
    Activations Density 0.000%

    No Known Activations