© 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. 100441
    Prev
    Next
    INDEX
    Explanations

    words followed by grammatical elements

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

    jobs and roles 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
     मैन
    0.58
     арен
    0.52
    मैन
    0.51
     Ман
    0.50
     isk
    0.47
    租
    0.47
     phát
    0.46
     hô
    0.46
     renter
    0.46
     치
    0.46
    POSITIVE LOGITS
     grungy
    0.52
    illustrations
    0.51
    slime
    0.51
     subsection
    0.50
     traduit
    0.49
     anciennes
    0.48
     Trotsky
    0.47
     অভিযুক্ত
    0.46
    img
    0.45
    /";
    0.44
    Activations Density 0.001%

    No Known Activations