© 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. 72363
    Prev
    Next
    INDEX
    Explanations

    places like Egypt and Dixie

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

    fluid pressure

    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
     FRIEND
    0.51
    ingles
    0.44
     другу
    0.44
     friendship
    0.43
     жел
    0.42
    ూర్
    0.41
    ﻟ
    0.41
    йда
    0.40
     샘
    0.40
     મુ
    0.39
    POSITIVE LOGITS
     सर्विसेज
    0.53
     swoich
    0.49
     konser
    0.49
    ফরম
    0.48
     vorne
    0.47
     বুলেট
    0.47
     ustaw
    0.47
     zahlreichen
    0.46
     svojih
    0.46
     exécut
    0.46
    Activations Density 0.001%

    No Known Activations