© 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. 19659
    Prev
    Next
    INDEX
    Explanations

    offers all-in-one security

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

    Technical complexity, premium pricing, slow performance

    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
    polymer
    0.53
    気
    0.47
    u
    0.45
    r
    0.43
    on
    0.42
    o
    0.42
    PM
    0.42
    或是
    0.41
    Makefile
    0.41
    analog
    0.41
    POSITIVE LOGITS
     podpis
    0.56
     Empress
    0.51
     konum
    0.50
     അഭ
    0.49
     Gallup
    0.49
     Lobkowicz
    0.48
     Hmm
    0.47
     Henrietta
    0.47
     çağ
    0.46
     Immac
    0.46
    Activations Density 0.001%

    No Known Activations