© 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. 21150
    Prev
    Next
    INDEX
    Explanations

    reasons for actions

    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
     మూడు
    0.48
     стоимо
    0.47
     видим
    0.47
     ત્રણ
    0.47
     היי
    0.46
    这家
    0.45
    跚
    0.45
    <unused1743>
    0.45
     четыре
    0.45
    <unused2015>
    0.45
    POSITIVE LOGITS
     frequently
    0.44
    assets
    0.42
    经常
    0.41
    :
    0.41
    使用
    0.40
     lenders
    0.40
     vessels
    0.39
    ο
    0.39
    mj
    0.39
    @
    0.38
    Activations Density 0.003%

    No Known Activations