© 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-65K
    7. 62758
    Prev
    Next
    INDEX
    Explanations

    questions and understanding

    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_65k_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
    <unused46>
    0.44
     강
    0.40
    ВС
    0.40
     olmasına
    0.40
    푹
    0.38
    억원
    0.38
    등
    0.37
    만원
    0.37
     contemplate
    0.36
     라
    0.36
    POSITIVE LOGITS
     this
    0.58
    了这个
    0.57
     この
    0.54
    它的
    0.53
    :
    0.52
    この
    0.52
     The
    0.48
     এই
    0.48
     This
    0.47
     the
    0.46
    Activations Density 0.013%

    No Known Activations