© 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. 219569
    Prev
    Next
    INDEX
    Explanations

    first opening, previously disclosed, scenario practically

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

    unless specifically older

    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
     Geç
    0.50
    佹
    0.50
    יו
    0.49
     mò
    0.48
    ني
    0.48
    威
    0.47
    過去
    0.47
     étend
    0.46
    U
    0.46
     geçen
    0.46
    POSITIVE LOGITS
    ércio
    0.49
    fromParams
    0.48
    licer
    0.47
     یار
    0.47
    adhi
    0.46
    edic
    0.45
     باور
    0.45
    amme
    0.45
     مذہ
    0.45
    abortion
    0.44
    Activations Density 0.001%

    No Known Activations