© 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. 164945
    Prev
    Next
    INDEX
    Explanations

    lawyer fees, every case

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

    deployment, Cascade, defending, end

    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
    ü
    0.59
    üd
    0.51
    ylsulfanyl
    0.50
    ifrån
    0.50
    üb
    0.49
    ül
    0.48
    ermanfaat
    0.48
    äch
    0.47
    advance
    0.47
    ab
    0.47
    POSITIVE LOGITS
    وك
    0.50
    جري
    0.50
     “
    0.47
    绎
    0.46
     jornal
    0.44
     roundabout
    0.44
     résident
    0.44
     كه
    0.43
     groupes
    0.43
     novem
    0.42
    Activations Density 0.000%

    No Known Activations