© 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. 110357
    Prev
    Next
    INDEX
    Explanations

    first sentences

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

    building APIs

    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
    𝚕
    0.55
     liné
    0.53
    を用いた
    0.48
     attribution
    0.47
     общения
    0.47
     travaillons
    0.46
    唿
    0.46
     rosas
    0.45
     busque
    0.44
    둴
    0.44
    POSITIVE LOGITS
    ಂದರೆ
    0.55
    irst
    0.50
     Pandora
    0.49
    idu
    0.49
     DIST
    0.47
     BIN
    0.46
    iding
    0.45
     Skinner
    0.45
     DAS
    0.45
    ides
    0.44
    Activations Density 0.001%

    No Known Activations