© 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. 224257
    Prev
    Next
    INDEX
    Explanations

    signing documents or contracts

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

    provider, insurer, customer

    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
    Ça
    0.59
    Н
    0.56
    Це
    0.53
    颓
    0.51
     інших
    0.50
    З
    0.50
     полити
    0.48
    Thesis
    0.48
     स
    0.46
    agangan
    0.46
    POSITIVE LOGITS
     giphy
    0.55
     onboarding
    0.54
     marshmallow
    0.53
     Figma
    0.52
     provider
    0.52
     quercetin
    0.50
     phishing
    0.49
     gummies
    0.48
     gummy
    0.48
     signage
    0.48
    Activations Density 0.002%

    No Known Activations