© 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. 88666
    Prev
    Next
    INDEX
    Explanations

    social identities and discourse

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

    questions and code

    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
     ব্যবহারের
    0.51
    启用
    0.46
    -
    0.44
     ორგანო
    0.43
    ARIA
    0.42
     всіх
    0.41
     hören
    0.41
    Eras
    0.40
     описы
    0.39
    Ū
    0.39
    POSITIVE LOGITS
    0
    0.50
     Neh
    0.45
    guys
    0.44
    ancial
    0.44
     Ney
    0.44
     ifs
    0.44
    current
    0.43
    twitter
    0.43
    confusion
    0.43
    igay
    0.43
    Activations Density 0.000%

    No Known Activations