© 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. 128678
    Prev
    Next
    INDEX
    Explanations

    admissible easy directly small playlist

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

    hypotheses

    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
     DK
    0.46
     II
    0.44
     Ally
    0.44
     III
    0.44
     astrocytes
    0.43
     air
    0.43
     Poi
    0.43
     Ό
    0.42
    pc
    0.42
     testis
    0.42
    POSITIVE LOGITS
    ську
    0.54
     نخست
    0.51
     бекер
    0.51
    ське
    0.50
     angesehen
    0.49
     hundert
    0.49
    ських
    0.48
     публі
    0.47
    ürnberg
    0.47
    ські
    0.46
    Activations Density 0.000%

    No Known Activations