© 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. 169013
    Prev
    Next
    INDEX
    Explanations

    Asian secret society, dragons, tracking

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

    describe or implement

    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
     consistente
    0.50
    𝐳
    0.46
     प्लस
    0.44
    ј
    0.44
     نوف
    0.44
    zoeken
    0.43
    nov
    0.43
     cuadrados
    0.43
     rebounded
    0.43
     regreso
    0.43
    POSITIVE LOGITS
     relais
    0.45
    典型
    0.45
     전통
    0.42
    発達
    0.42
    enment
    0.42
     রচিত
    0.42
    ="#
    0.42
    듦
    0.42
    伝統
    0.42
     fraternity
    0.42
    Activations Density 0.000%

    No Known Activations