© 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. 94748
    Prev
    Next
    INDEX
    Explanations

    costs, prices, defects, damages

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

    text descriptions following certain words

    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
     seroton
    0.50
     वापसी
    0.46
    amerika
    0.45
     Амери
    0.45
    砣
    0.45
    शिंगटन
    0.44
     hiki
    0.44
     ఆ
    0.44
     azules
    0.43
    رفه
    0.43
    POSITIVE LOGITS
     source
    0.45
     Zach
    0.42
     Reconstruction
    0.41
     sources
    0.41
     Hertz
    0.41
    ORI
    0.39
     meticulously
    0.38
     Feldman
    0.38
     Standardization
    0.38
     standardization
    0.38
    Activations Density 0.003%

    No Known Activations