© 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. 164594
    Prev
    Next
    INDEX
    Explanations

    calling families, decided to, dealing only

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

    rare genetic, USAP, relation to, fruits are, off the, on the

    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
    apes
    0.44
    aes
    0.44
    ;
    0.44
    T
    0.43
    com
    0.43
    Hyundai
    0.42
     Hyundai
    0.40
     apertures
    0.40
    coats
    0.39
     Peugeot
    0.38
    POSITIVE LOGITS
     नोन
    0.53
    RequestHandler
    0.52
     richieste
    0.52
     respondió
    0.51
    harusnya
    0.50
     decidió
    0.49
    埛
    0.49
     SHALL
    0.49
     ANY
    0.48
     hizo
    0.48
    Activations Density 0.001%

    No Known Activations