© 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. 196332
    Prev
    Next
    INDEX
    Explanations

    indicator light

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

    molecular formula

    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
     entree
    0.48
     onboard
    0.46
    sea
    0.44
     strides
    0.44
     सागरी
    0.44
     sea
    0.44
    ミ
    0.44
     percents
    0.43
     стари
    0.43
    シ
    0.42
    POSITIVE LOGITS
     Bigg
    0.50
     Wehr
    0.49
     abhäng
    0.48
     Schn
    0.48
     Pomer
    0.47
     kterou
    0.47
     Atom
    0.47
     Batter
    0.47
     Brenner
    0.46
     മാത്ര
    0.46
    Activations Density 0.000%

    No Known Activations