© 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. 199788
    Prev
    Next
    INDEX
    Explanations

    Kosovo declared

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

    compiling lists

    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
     اخر
    0.51
    撷
    0.47
     Gesamt
    0.45
     Gesam
    0.45
    مش
    0.45
     بم
    0.44
    issement
    0.43
     bodybuilding
    0.43
    لاسه
    0.42
    فران
    0.42
    POSITIVE LOGITS
    or
    0.51
    od
    0.48
    c
    0.48
    ome
    0.47
    aj
    0.47
    ünk
    0.47
     necesitamos
    0.46
    ant
    0.46
    answers
    0.45
    ujjati
    0.45
    Activations Density 0.001%

    No Known Activations