© 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. 164978
    Prev
    Next
    INDEX
    Explanations

    discovered

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

    early history or stages

    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
    dT
    0.48
    ViewModels
    0.43
    躲
    0.43
    噢
    0.43
    ubat
    0.43
    Rationale
    0.42
    參数
    0.41
     doe
    0.41
        
    0.40
    erny
    0.40
    POSITIVE LOGITS
     Merrill
    0.48
    今年は
    0.47
    ಉ
    0.47
    年
    0.47
     વર્ષ
    0.47
     Hodges
    0.47
     аген
    0.47
    まず
    0.46
    今年
    0.45
     agli
    0.45
    Activations Density 0.001%

    No Known Activations