© 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. 51772
    Prev
    Next
    INDEX
    Explanations

    names followed by descriptions

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

    leap year

    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
    KAR
    0.49
    ed
    0.49
    Histoire
    0.49
    Tennessee
    0.47
    కులు
    0.47
    edil
    0.46
    (&
    0.45
     μεγάλη
    0.45
     津
    0.45
     stanie
    0.44
    POSITIVE LOGITS
     parametrization
    0.47
     quantitatively
    0.45
     computation
    0.44
     functioning
    0.43
     regularization
    0.42
     elves
    0.42
     workstation
    0.42
     vaporization
    0.41
    さは
    0.41
     kayaks
    0.41
    Activations Density 0.000%

    No Known Activations