© 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. 61694
    Prev
    Next
    INDEX
    Explanations

    arthur for, the crescent/brand/arena, of Riva, softer FX

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

    common sense scenarios

    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
    shifted
    0.54
    трима
    0.52
    пере
    0.52
    initiated
    0.51
    adopted
    0.51
    ܤ
    0.51
    цент
    0.50
    averaged
    0.49
    פ
    0.48
    deleted
    0.48
    POSITIVE LOGITS
     e
    0.57
     করোনা
    0.48
     European
    0.47
     Temperature
    0.46
    achadh
    0.46
     Polish
    0.45
     Barley
    0.45
     Reth
    0.45
     Mother
    0.45
     Temperatures
    0.45
    Activations Density 0.000%

    No Known Activations