© 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. 203180
    Prev
    Next
    INDEX
    Explanations

    past game counts

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

    contrary but it

    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
     نیاز
    0.44
     و
    0.42
     ನಾಲ್
    0.42
     těž
    0.41
     mấy
    0.41
    ...',
    0.41
    6
    0.41
     möglicherweise
    0.40
    1
    0.40
     schweren
    0.40
    POSITIVE LOGITS
    нат
    0.52
     EDUC
    0.51
    мери
    0.48
    ણી
    0.46
    Ψ
    0.45
    acti
    0.44
     reprises
    0.44
    ુર
    0.43
    йга
    0.43
    晔
    0.42
    Activations Density 0.006%

    No Known Activations