© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 188388
    Prev
    Next
    INDEX
    Explanations

    being further inland

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

    intended use, safety, cable, driver

    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
     স
    0.52
     scaled
    0.51
     venezol
    0.49
     escala
    0.47
    బ
    0.47
     ridges
    0.46
     uten
    0.46
    гти
    0.46
    的版本
    0.45
    ุปกรณ์
    0.45
    POSITIVE LOGITS
     in
    0.55
     govern
    0.51
    Harvard
    0.51
    title
    0.49
    tracer
    0.49
    ♯
    0.49
    determine
    0.48
     Biology
    0.47
    liament
    0.46
    cert
    0.46
    Activations Density 0.001%

    No Known Activations