© 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. 155116
    Prev
    Next
    INDEX
    Explanations

    robust way

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

    foreign characters and 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
    asis
    0.48
    viation
    0.48
     расстояние
    0.46
     向
    0.46
     ಮೊದಲ
    0.45
    向
    0.45
    wirkung
    0.45
    olong
    0.42
    ('-
    0.42
    r
    0.41
    POSITIVE LOGITS
     aventuras
    0.47
     ensembles
    0.47
     nejen
    0.45
     operadores
    0.44
     organes
    0.44
     nerdy
    0.44
     recuperar
    0.43
     fosse
    0.42
     vele
    0.42
     analyzers
    0.41
    Activations Density 0.002%

    No Known Activations