© 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. 114799
    Prev
    Next
    INDEX
    Explanations

    daily occurrence

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

    phrases ending punctuation

    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
    équ
    0.48
    nolds
    0.47
    lin
    0.46
    ↵
    0.45
    cd
    0.45
    diag
    0.44
     ,
    0.44
    est
    0.43
    cure
    0.43
    fin
    0.43
    POSITIVE LOGITS
    Viele
    0.49
    Seperti
    0.48
    Ꮴ
    0.47
     terlibat
    0.47
    Những
    0.46
     어린
    0.46
     участь
    0.45
    Algun
    0.44
    Với
    0.44
    Kiza
    0.44
    Activations Density 0.000%

    No Known Activations