© 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. 26739
    Prev
    Next
    INDEX
    Explanations

    detecting word pairings

    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
    instant
    0.65
    ID
    0.55
    Instant
    0.50
    novation
    0.46
    5
    0.46
     Instant
    0.45
    AP
    0.45
    0
    0.44
    emia
    0.44
    PNG
    0.44
    POSITIVE LOGITS
     mime
    0.43
     Waterman
    0.42
     finalList
    0.42
    <unused21>
    0.41
     frutas
    0.41
     ceux
    0.41
     réfl
    0.41
     psico
    0.40
     slij
    0.40
     লিও
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.