© 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. 36222
    Prev
    Next
    INDEX
    Explanations

    specific subsequent phrases

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

    formats and documentation

    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
    y
    0.67
    ori
    0.54
    ta
    0.53
    o
    0.53
    å
    0.51
    nbr
    0.51
    UIColor
    0.50
    do
    0.50
    e
    0.49
    pan
    0.49
    POSITIVE LOGITS
     linge
    0.51
     véd
    0.50
     certiorari
    0.50
     Kral
    0.50
     rudimentary
    0.49
    лением
    0.48
     practicable
    0.47
    Microelectronics
    0.47
     realism
    0.47
     discs
    0.47
    Activations Density 0.000%

    No Known Activations