© 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. 23891
    Prev
    Next
    INDEX
    Explanations

    Detailed information

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

    list of choices: ways, acronym, packages, touch

    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
    扃
    0.52
    বিনোদন
    0.46
    Beyblade
    0.46
    उंड
    0.45
    віт
    0.44
     Shout
    0.44
    Deletion
    0.44
     населення
    0.44
    鋁
    0.44
    𝑤
    0.44
    POSITIVE LOGITS
     könne
    0.52
     recommandations
    0.50
     procur
    0.48
    olphe
    0.47
     gratu
    0.47
     diversa
    0.46
     certific
    0.46
     zapewn
    0.46
     protections
    0.46
     capables
    0.46
    Activations Density 0.000%

    No Known Activations