© 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. 181123
    Prev
    Next
    INDEX
    Explanations

    starting activities

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

    wish to travel

    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
    c
    0.57
    avasena
    0.55
    ool
    0.47
    abis
    0.47
    has
    0.47
    oha
    0.47
    za
    0.46
     វា
    0.45
    e
    0.45
    ath
    0.45
    POSITIVE LOGITS
     cerebellar
    0.55
     nucleotides
    0.53
     nucleotide
    0.52
     мебель
    0.52
     deuteron
    0.49
     мебели
    0.49
     لوبې
    0.48
     libido
    0.48
     diphtheria
    0.47
     nuclé
    0.46
    Activations Density 0.001%

    No Known Activations