© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    possessive or prepositional phrases

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

    abstract concepts and connectors

    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
     খুবই
    0.40
     매우
    0.40
     ඉතා
    0.39
    ³.
    0.38
     ძალიან
    0.38
    非常に
    0.37
    மிக
    0.37
    𝐧
    0.37
     très
    0.37
     дуже
    0.37
    POSITIVE LOGITS
     для
    0.44
     của
    0.41
     ntawm
    0.40
     нашей
    0.39
     naszym
    0.38
    のは
    0.37
     untuk
    0.37
     pentru
    0.37
    したのは
    0.37
     لل
    0.36
    Activations Density 0.054%

    No Known Activations