© 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. 32840
    Prev
    Next
    INDEX
    Explanations

    parameters of

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

    DNA analysis

    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
    ↵↵
    0.50
    burg
    0.48
     WAL
    0.45
    
    0.44
    burgh
    0.43
     Studenten
    0.43
     blackmail
    0.43
    ．
    0.42
     polit
    0.42
     traditionnel
    0.42
    POSITIVE LOGITS
    运作
    0.52
     parámetro
    0.52
    식
    0.51
    구성
    0.50
    یم
    0.50
    posición
    0.50
     اختيار
    0.50
     কূপ
    0.49
     parámetros
    0.48
     إجراء
    0.47
    Activations Density 0.000%

    No Known Activations