© 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. 224647
    Prev
    Next
    INDEX
    Explanations

    years old

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

    adverb + verb/concept

    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
    {
    0.46
     बताऊंगा
    0.43
    Frame
    0.43
     zabez
    0.42
    Gur
    0.42
    Departments
    0.42
    Please
    0.42
     jednego
    0.42
    Tere
    0.42
     ty
    0.42
    POSITIVE LOGITS
     desaparecido
    0.46
    зом
    0.45
     Gómez
    0.44
    เพราะ
    0.43
     আমলে
    0.43
     ‎
    0.43
     ISO
    0.42
     Ingram
    0.41
     perdido
    0.41
     Schmitt
    0.41
    Activations Density 0.000%

    No Known Activations