© 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. 7246
    Prev
    Next
    INDEX
    Explanations

    noun followed by state or action

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

    describing states of nouns

    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
     بتوان
    0.28
    ۔
    0.27
    ።
    0.27
    これにより
    0.26
     puissent
    0.26
    噉
    0.25
     ermöglichen
    0.25
    ܀
    0.24
    ।
    0.24
    。
    0.24
    POSITIVE LOGITS
     is
    0.38
     wasn
    0.38
     είναι
    0.38
     isn
    0.37
     was
    0.36
     seems
    0.36
     didn
    0.35
     had
    0.34
     hasn
    0.34
     doesn
    0.33
    Activations Density 0.617%

    No Known Activations