© 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. 160825
    Prev
    Next
    INDEX
    Explanations

    noun suffixes followed by common words

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

    Okay starting model responses

    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
    케
    0.46
     케
    0.45
    legas
    0.45
    нт
    0.44
    뮐
    0.43
    ཎ
    0.43
    يث
    0.43
    ಲ್ಲು
    0.42
    𝚗
    0.42
     ސ
    0.42
    POSITIVE LOGITS
     Treasures
    0.48
     (
    0.44
     educated
    0.44
     Blanca
    0.40
     نمای
    0.40
     Minh
    0.39
     Riche
    0.39
    ตั้งแต่
    0.39
     August
    0.38
     Intent
    0.38
    Activations Density 0.001%

    No Known Activations