© 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. 223801
    Prev
    Next
    INDEX
    Explanations

    Dad, beach, boat, cove

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

    direct relationship or potential

    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
    瞞
    0.53
     pept
    0.52
     evitar
    0.52
     peptid
    0.51
     proteolytic
    0.50
     operand
    0.50
     хро
    0.49
     traditions
    0.48
     alkaloids
    0.47
     arginine
    0.47
    POSITIVE LOGITS
     Dad
    0.49
    s
    0.48
     Beach
    0.47
     Boat
    0.46
    라면
    0.46
     Cove
    0.45
     renew
    0.45
    Beach
    0.45
    Ꮷ
    0.44
    Dad
    0.44
    Activations Density 0.001%

    No Known Activations