© 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. 201005
    Prev
    Next
    INDEX
    Explanations

    new year, holidays

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

    conditional logic keywords

    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
     CI
    0.51
     超
    0.47
     রায়
    0.45
     Harrison
    0.45
     পি
    0.44
     Ci
    0.44
    Harrison
    0.43
     zaak
    0.43
     Paryayvachi
    0.43
    ORS
    0.42
    POSITIVE LOGITS
     waterline
    0.55
    если
    0.51
     contracts
    0.48
     работу
    0.48
     stockpile
    0.47
    ээ
    0.46
    ט
    0.45
     concerts
    0.44
    لى
    0.44
    как
    0.44
    Activations Density 0.001%

    No Known Activations