© 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. 165467
    Prev
    Next
    INDEX
    Explanations

    services or information

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

    greeting texts

    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
    oley
    0.49
     continúa
    0.49
     گیرد
    0.49
     オール
    0.49
     "":
    0.49
     เหมาะ
    0.49
    सभी
    0.48
     `/
    0.48
    लू
    0.48
     ĝi
    0.47
    POSITIVE LOGITS
    頑
    0.48
    艱
    0.48
    蕭
    0.47
    深刻
    0.47
    怎樣
    0.45
     sagen
    0.45
    冗
    0.42
    節
    0.42
    痛苦
    0.41
     wirtschaft
    0.41
    Activations Density 0.000%

    No Known Activations