© 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. 64759
    Prev
    Next
    INDEX
    Explanations

    official language

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

    browsing capabilities, product integrations, supplemental education, private groups

    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
     COMO
    0.48
     ayrıca
    0.48
     tanpa
    0.45
     anche
    0.44
     искусства
    0.44
     वसू
    0.43
     ใ
    0.43
     yakın
    0.43
     whim
    0.43
    creet
    0.43
    POSITIVE LOGITS
    ંગ
    0.56
    렌
    0.44
    MP
    0.44
    verhalten
    0.43
    AT
    0.42
    트
    0.42
    ంలో
    0.42
    제로
    0.42
    里程
    0.42
     accel
    0.42
    Activations Density 0.000%

    No Known Activations