© 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. 251943
    Prev
    Next
    INDEX
    Explanations

    rules and policies

    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
    InfoPlistPath
    0.52
     Ettha
    0.51
    唃
    0.51
     снять
    0.50
     Spade
    0.48
     Pointe
    0.47
     খুঁজতে
    0.47
    玤
    0.47
    วิ
    0.46
     নিরাপদ
    0.46
    POSITIVE LOGITS
    0.50
    ore
    0.48
    都
    0.48
    cou
    0.48
    tweets
    0.47
    are
    0.47
    att
    0.46
    ethn
    0.46
    б
    0.45
    й
    0.44
    Activations Density 0.001%

    No Known Activations