© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82089
    Prev
    Next
    INDEX
    Explanations

    technical terms and titles

    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
    ᱗
    0.48
    ージ
    0.47
    ᱕
    0.47
    라
    0.46
     минуты
    0.44
    ສ
    0.43
    넌
    0.43
    𝘃
    0.43
    지만
    0.43
    CM
    0.43
    POSITIVE LOGITS
     ያስፈል
    0.46
    ättning
    0.45
    arem
    0.45
     tarko
    0.44
    鲑
    0.44
    äischen
    0.43
    ěn
    0.43
    ا۔
    0.43
    Alien
    0.42
     ඇත
    0.41
    Activations Density 0.001%

    No Known Activations