© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4651
    Prev
    Next
    INDEX
    Explanations

    at the

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

    phrases starting with at

    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
    ými
    0.52
     IncludeField
    0.52
    fromParams
    0.47
    就没有
    0.46
    লিখিত
    0.45
    封装
    0.44
     vych
    0.44
    妷
    0.44
     dynast
    0.43
     می‌کند
    0.43
    POSITIVE LOGITS
     behest
    0.83
     this
    0.70
    rocities
    0.67
     intervals
    0.66
     at
    0.66
    f
    0.65
     crossroads
    0.63
     outset
    0.63
    na
    0.61
    kinson
    0.61
    Activations Density 0.555%

    No Known Activations