© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    qualifiers for magnitude or degree

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

    questions, explanations, or medical terms

    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
    妞
    0.50
    จ
    0.46
    冲
    0.45
     MAKING
    0.45
    โน
    0.42
     ด
    0.41
     этого
    0.41
    ชา
    0.41
    ﻨ
    0.41
    VE
    0.41
    POSITIVE LOGITS
     analgesic
    0.47
     glucocortic
    0.46
    orcid
    0.45
     pengendalian
    0.45
     immunore
    0.44
    renerg
    0.43
     pharmacokinetic
    0.43
    regulatory
    0.42
     Hadamard
    0.42
     বিক্ষোভ
    0.42
    Activations Density 0.000%

    No Known Activations