© 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. 200586
    Prev
    Next
    INDEX
    Explanations

    social services, company information

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

    communication and social media platforms

    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
    하
    0.56
     ریکارڈ
    0.49
    ለያ
    0.49
    0.49
    カウント
    0.49
    ハ
    0.48
    static
    0.48
     mount
    0.47
     रिकॉर्ड
    0.46
    邳
    0.46
    POSITIVE LOGITS
     quen
    0.48
     единица
    0.45
    ichte
    0.45
     Quotient
    0.45
     ü
    0.44
    risch
    0.44
    üdis
    0.44
     Einheit
    0.44
     abond
    0.43
     ఇందులో
    0.43
    Activations Density 0.000%

    No Known Activations