© 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. 94695
    Prev
    Next
    INDEX
    Explanations

    have you experienced

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

    have you been

    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
     in
    0.68
    0
    0.60
    at
    0.50
     able
    0.49
     في
    0.48
     Bex
    0.47
    bricks
    0.47
    9
    0.47
     new
    0.47
    icken
    0.47
    POSITIVE LOGITS
     been
    1.32
     BEEN
    1.29
     Been
    1.23
    been
    1.17
    Been
    1.17
     fått
    0.93
     varit
    0.80
     været
    0.80
     vært
    0.79
     avuto
    0.73
    Activations Density 0.183%

    No Known Activations