© 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. 163090
    Prev
    Next
    INDEX
    Explanations

    enterprise combined, towards international

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

    crucial piece, associated with, helps calculations

    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
    व
    0.50
    대
    0.49
    द
    0.49
    인
    0.45
     존재
    0.43
    み
    0.42
    اری
    0.42
    dn
    0.42
    isiones
    0.42
    Ĝ
    0.41
    POSITIVE LOGITS
     eBook
    0.52
     ശങ്ക
    0.49
     outfitted
    0.49
     গ্রাহ
    0.48
     recast
    0.47
     ساين
    0.47
    SecurityCenter
    0.47
     Recover
    0.47
     খাবারের
    0.46
     বাড়তি
    0.46
    Activations Density 0.000%

    No Known Activations