© 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. 197865
    Prev
    Next
    INDEX
    Explanations

    describing state or condition

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

    phrases and incorrect spellings

    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
    }{
    0.44
    labs
    0.43
    }^{+}\
    0.43
    credited
    0.42
    enced
    0.41
    жного
    0.41
    rat
    0.41
    κ
    0.40
    witness
    0.40
    axos
    0.40
    POSITIVE LOGITS
     separations
    0.50
    ালি
    0.48
     commitments
    0.47
     Commit
    0.47
    씰
    0.46
     runny
    0.45
     цена
    0.44
     cliquer
    0.44
    Цена
    0.43
     pulls
    0.43
    Activations Density 0.002%

    No Known Activations