© 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. 55311
    Prev
    Next
    INDEX
    Explanations

    leading visionary agendas

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

    API endpoints needed

    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
    likes
    0.44
    แท
    0.44
    stick
    0.44
    เร
    0.42
    thousands
    0.42
    oming
    0.42
     consumes
    0.42
    :
    0.42
    🛡
    0.42
    low
    0.42
    POSITIVE LOGITS
    ЕР
    0.47
     gennaio
    0.46
     yazd
    0.45
    اليا
    0.44
     mendek
    0.44
     extrad
    0.44
    دیا
    0.43
     específicas
    0.43
    檐
    0.43
     faptul
    0.42
    Activations Density 0.000%

    No Known Activations