© 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. 100363
    Prev
    Next
    INDEX
    Explanations

    understanding and browsing services

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

    diagnostic information, applying for, started demanding

    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
     思う
    0.52
     IX
    0.50
     Begin
    0.48
     BEGIN
    0.48
     VIII
    0.47
     సంవ
    0.46
    idez
    0.46
     緑
    0.46
     這個
    0.46
    ular
    0.45
    POSITIVE LOGITS
    νά
    0.45
    ล
    0.45
    ल
    0.45
    Fortune
    0.45
    нг
    0.44
    mounting
    0.43
    scoped
    0.43
    लिस
    0.42
     masala
    0.42
    ო
    0.42
    Activations Density 0.000%

    No Known Activations