© 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. 241994
    Prev
    Next
    INDEX
    Explanations

    semester abroad

    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
    sächlich
    0.50
    Delimiter
    0.49
    getSeconds
    0.49
    MinIntensity
    0.48
    ariamente
    0.46
    Recipient
    0.46
    Versions
    0.45
    𝒮
    0.45
     पॉजिटिव
    0.44
    LoginForm
    0.44
    POSITIVE LOGITS
     s
    0.54
     we
    0.54
     ding
    0.51
     ba
    0.50
     journalism
    0.49
     PHD
    0.48
     zda
    0.48
     Mexico
    0.48
     tale
    0.47
     walled
    0.47
    Activations Density 0.000%

    No Known Activations