© 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. 137794
    Prev
    Next
    INDEX
    Explanations

    looking for information

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

    striving for, suggest useful, respond better

    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
     warned
    0.45
     밑
    0.44
     adhesives
    0.43
     manufacturers
    0.43
     calibrated
    0.41
     three
    0.41
     under
    0.41
     moist
    0.41
     pendant
    0.41
     parallelogram
    0.41
    POSITIVE LOGITS
    琐
    0.52
     तारीख
    0.50
     yaşanan
    0.47
     Editar
    0.46
     있다
    0.45
    Artista
    0.45
     시절
    0.44
     있기
    0.44
     दाता
    0.44
     DATE
    0.43
    Activations Density 0.000%

    No Known Activations