© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33336
    Prev
    Next
    INDEX
    Explanations

    dating sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řád
    -1.01
    poved
    -0.93
    ToFile
    -0.91
    take
    -0.88
     защото
    -0.88
     añ
    -0.86
    träger
    -0.86
    Topology
    -0.86
    dad
    -0.85
     emberek
    -0.85
    POSITIVE LOGITS
    このまま
    0.93
    When
    0.92
    During
    0.92
     コーディネート
    0.90
     other
    0.88
    うまく
    0.88
     Within
    0.87
    ffl
    0.86
     During
    0.85
     내용
    0.85
    Activations Density 0.002%

    No Known Activations