© 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. 244242
    Prev
    Next
    INDEX
    Explanations

    Floridian HR side selected victory targets for

    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
     সন্ত্রাসী
    0.50
    乖
    0.48
    𒅀
    0.47
     полови
    0.46
     IntegerValue
    0.46
     половины
    0.45
     অভাবে
    0.44
     መሰ
    0.44
     সাহিত্যের
    0.44
    PlainText
    0.43
    POSITIVE LOGITS
    ют
    0.53
    an
    0.50
    EM
    0.49
     filoz
    0.47
     um
    0.47
     uma
    0.47
    /$
    0.47
    around
    0.46
     siden
    0.46
    วั
    0.46
    Activations Density 0.000%

    No Known Activations