© 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. 89853
    Prev
    Next
    INDEX
    Explanations

    creation, certificates, discussion about fees

    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
    િયન
    0.52
    美国
    0.47
    ,{
    0.43
    סטר
    0.42
     arquivos
    0.42
     понял
    0.41
    侃
    0.41
    犁
    0.41
    éa
    0.41
    故事
    0.40
    POSITIVE LOGITS
    high
    0.48
    meals
    0.47
    foods
    0.46
     पार्टियों
    0.45
     Шо
    0.44
    fills
    0.44
     रेग
    0.43
     শোভ
    0.43
    স্বাধীন
    0.43
     পেট্র
    0.43
    Activations Density 0.001%

    No Known Activations