© 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. 71709
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

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

    still or list

    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
     únicas
    0.50
     apesar
    0.46
     {}>,
    0.46
     cuidadosamente
    0.45
    بے
    0.44
    虾
    0.43
     overdose
    0.43
     gerçekten
    0.43
     tornando
    0.42
     riqueza
    0.42
    POSITIVE LOGITS
    oe
    0.51
    ues
    0.48
    loe
    0.47
    ages
    0.47
    rict
    0.46
     prevention
    0.46
     軍
    0.46
    ius
    0.46
    oa
    0.45
    rhein
    0.45
    Activations Density 0.001%

    No Known Activations