© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    brokers and financial statements

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

    lifestyle intervention and self-management

    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
    သုံး
    0.44
     تجاوز
    0.41
     শত
    0.40
    带宽
    0.39
    銃
    0.39
     মিলিয়ন
    0.39
    㳳
    0.38
    千萬
    0.38
     गहरी
    0.38
     میلیون
    0.38
    POSITIVE LOGITS
     recognised
    0.39
    ulation
    0.39
     thok
    0.37
     hergestellt
    0.36
     clarified
    0.36
    <0xE1>
    0.35
     angesehen
    0.35
     bet
    0.34
     reff
    0.34
     misinterpreted
    0.34
    Activations Density 0.009%

    No Known Activations