© 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. 21580
    Prev
    Next
    INDEX
    Explanations

    between concepts or things

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

    combining multiple concepts

    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
    í
    0.41
     സ്ഥി
    0.41
     posteriores
    0.38
     násled
    0.38
     în
    0.38
     éché
    0.38
     GmbH
    0.37
     í
    0.37
     één
    0.37
     müm
    0.37
    POSITIVE LOGITS
    between
    0.68
     between
    0.68
     antara
    0.67
     combination
    0.65
    combination
    0.65
     BETWEEN
    0.63
     giữa
    0.62
     tussen
    0.62
     zwischen
    0.62
     између
    0.60
    Activations Density 0.074%

    No Known Activations