© 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. 197417
    Prev
    Next
    INDEX
    Explanations

    listing classes, discussion of, limited service broker

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

    put money into

    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
     inhom
    0.60
     BLUENRG
    0.59
     inhomogeneities
    0.52
     Америки
    0.51
     mism
    0.49
     angust
    0.49
    误
    0.49
     Stamps
    0.48
     annih
    0.48
     imped
    0.48
    POSITIVE LOGITS
    mon
    0.52
    host
    0.51
    broadcast
    0.51
    moving
    0.49
    hex
    0.49
    become
    0.49
    I
    0.48
    bach
    0.48
    byteArray
    0.48
    Become
    0.47
    Activations Density 0.000%

    No Known Activations