© 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. 127656
    Prev
    Next
    INDEX
    Explanations

    motion, early, deleted, from, contact, company, ready

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

    offering to help or contribute

    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
    ییر
    0.51
    𐰃
    0.50
     ponen
    0.46
     Caedwalla
    0.46
     wheelchair
    0.45
     ここ
    0.45
     rezult
    0.45
     tepung
    0.45
     dobrze
    0.45
     dandelion
    0.44
    POSITIVE LOGITS
    odet
    0.47
    a
    0.46
    ter
    0.44
    version
    0.43
    ún
    0.43
    ición
    0.43
     individualized
    0.42
    ama
    0.42
    ás
    0.41
    áf
    0.41
    Activations Density 0.003%

    No Known Activations