© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110931
    Prev
    Next
    INDEX
    Explanations

    financial, technical, and descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unele
    0.54
    gå
    0.46
    klahoma
    0.46
     nawet
    0.45
    ภา
    0.44
    Hö
    0.44
    吼
    0.43
     lov
    0.43
    レ
    0.42
     més
    0.42
    POSITIVE LOGITS
     केसर
    0.47
    np
    0.45
    લ
    0.44
     enroll
    0.44
    certs
    0.44
    duh
    0.43
     क्ष
    0.42
     структура
    0.42
     сорти
    0.42
     rightly
    0.41
    Activations Density 0.002%

    No Known Activations