© 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. 111584
    Prev
    Next
    INDEX
    Explanations

    subsequently transferred

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

    my current existence

    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
     совсем
    0.59
     政
    0.51
     мир
    0.50
     всё
    0.47
     갔
    0.46
     ሥ
    0.46
     源
    0.46
     memasuki
    0.45
     zupeł
    0.45
     hormati
    0.45
    POSITIVE LOGITS
    т
    0.51
     Arthritis
    0.49
    দ
    0.49
    ლებ
    0.48
    ixen
    0.48
    טן
    0.47
     accrued
    0.46
     portability
    0.46
    letic
    0.46
     Lokal
    0.46
    Activations Density 0.001%

    No Known Activations