© 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. 34-GEMMASCOPE-RES-131K
    7. 78430
    Prev
    Next
    INDEX
    Explanations

    distant past and future

    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_34/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
     anschließend
    -0.71
    {(-
    -0.68
    ストン
    -0.68
     chạy
    -0.67
    above
    -0.67
    ół
    -0.66
    hli
    -0.65
    捱
    -0.65
    を中心に
    -0.65
     reservar
    -0.65
    POSITIVE LOGITS
     distant
    5.53
    distant
    4.38
     Distant
    3.63
     remote
    3.58
     дале
    3.25
    遠
    3.02
    remote
    2.92
    远
    2.84
     far
    2.80
    Remote
    2.64
    Activations Density 0.062%

    No Known Activations