© 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. 34498
    Prev
    Next
    INDEX
    Explanations

    lock in price or rate

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

    Installation instructions

    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
     výsled
    0.53
     sekund
    0.52
    倾
    0.52
     दिलों
    0.50
     illum
    0.49
     enlightened
    0.49
     scientifiques
    0.49
    न्नई
    0.49
     ramas
    0.48
     restre
    0.48
    POSITIVE LOGITS
    an
    0.66
    har
    0.55
    '
    0.51
    az
    0.50
    iu
    0.48
    a
    0.48
    maker
    0.48
    ai
    0.48
    haro
    0.48
    hoo
    0.47
    Activations Density 0.000%

    No Known Activations