© 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. 26428
    Prev
    Next
    INDEX
    Explanations

    styles and descriptions

    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
    ătur
    0.46
     τῶν
    0.42
    authUser
    0.42
    unca
    0.41
     लोकतांत्रिक
    0.41
    外国人
    0.40
    ֩
    0.40
    ंसी
    0.40
    外国
    0.39
    𝔞
    0.39
    POSITIVE LOGITS
     italics
    0.56
     surrounds
    0.56
     możemy
    0.54
     prefixes
    0.54
     upang
    0.52
     subsets
    0.51
     truncate
    0.51
     obso
    0.50
     contenant
    0.50
     suffixes
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.