© 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. 53656
    Prev
    Next
    INDEX
    Explanations

    year, sixteenth, prosecute, myth, morrow

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

    . followed by word

    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
     Ginsburg
    0.42
     ビ
    0.41
     休
    0.41
     BEGIN
    0.41
     Immobilien
    0.40
    सीपी
    0.40
     வாய்
    0.39
     モダン
    0.39
     鳥
    0.39
     Enrique
    0.39
    POSITIVE LOGITS
    ज्ञानिक
    0.42
     oluyor
    0.41
     reallocation
    0.38
    чиком
    0.38
     systemat
    0.38
     clientèle
    0.38
    i
    0.38
    backslash
    0.37
     altera
    0.37
    ﻷ
    0.37
    Activations Density 0.012%

    No Known Activations