© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and descriptions

    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
     the
    0.60
     be
    0.42
    1
    0.41
    )
    0.41
     to
    0.41
     for
    0.40
     or
    0.40
     that
    0.38
     User
    0.38
     can
    0.38
    POSITIVE LOGITS
     meriye
    0.45
     ແລະ
    0.42
     револю
    0.41
    ４
    0.41
    ۵
    0.41
     alegría
    0.40
     искусства
    0.40
    ៥
    0.40
     REGIUNI
    0.40
    vykor
    0.40
    Activations Density 0.072%

    No Known Activations