© 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. 125712
    Prev
    Next
    INDEX
    Explanations

    releases Palestinian prisoners

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

    Russian punctuation and formatting

    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
    ümüş
    0.55
    Imagem
    0.54
     温
    0.52
     immagine
    0.50
     giày
    0.48
    癃
    0.48
     sách
    0.47
     bookstores
    0.47
     গম্ভীর
    0.47
     inkjet
    0.47
    POSITIVE LOGITS
    ,$
    0.52
    ’
    0.48
    '
    0.47
    /.
    0.46
    ,.
    0.46
    [
    0.45
    ный
    0.44
     В
    0.42
    фо
    0.42
    >.
    0.41
    Activations Density 0.000%

    No Known Activations