© 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. 76580
    Prev
    Next
    INDEX
    Explanations

    business and financial terms

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

    specific categories or types

    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
    ᒐ
    0.49
    དང་
    0.47
     সংস্কৃতি
    0.47
     vertreten
    0.45
    簿
    0.45
     definitivamente
    0.44
    ಿ
    0.43
    نې
    0.42
     বৃত্তান্ত
    0.42
     definitely
    0.41
    POSITIVE LOGITS
     Lip
    0.54
     Lik
    0.54
     Mind
    0.50
     Joshua
    0.50
     Lot
    0.50
     lik
    0.48
     Sweat
    0.47
     Joseph
    0.46
     Entropy
    0.46
     Judge
    0.46
    Activations Density 0.001%

    No Known Activations