© 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. 166404
    Prev
    Next
    INDEX
    Explanations

    common continuations after specific words

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

    sigmoid, scope, worldwide

    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
    loggedin
    0.41
    國
    0.41
     altura
    0.41
    ૂર્ણ
    0.40
     প
    0.39
    х
    0.39
     stalk
    0.39
    altura
    0.39
    લ્પ
    0.39
     блю
    0.39
    POSITIVE LOGITS
     Founding
    0.49
    ından
    0.48
    𝔹
    0.47
     زیرا
    0.46
    ısından
    0.44
     दट
    0.43
     Federated
    0.43
    akkha
    0.42
    𝗕
    0.41
     Pavilion
    0.41
    Activations Density 0.001%

    No Known Activations