© 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. 146274
    Prev
    Next
    INDEX
    Explanations

    to receive

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

    dangerous terrain, rebuttals, poetic builds

    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
     Villas
    0.54
    &
    0.52
     MPs
    0.52
     D
    0.51
    ён
    0.49
     FDA
    0.48
     Arnold
    0.48
     I
    0.47
     –
    0.47
     Villa
    0.47
    POSITIVE LOGITS
     концентра
    0.57
    علی
    0.54
     différent
    0.53
    ریک
    0.52
    قاف
    0.51
    рус
    0.51
    রু
    0.51
    தெ
    0.50
     cerveau
    0.50
    UpSync
    0.50
    Activations Density 0.001%

    No Known Activations