© 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. 56824
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
     to
    0.73
    UM
    0.72
    SI
    0.68
     was
    0.66
    z
    0.62
    }$
    0.61
     has
    0.61
     v
    0.60
    de
    0.55
     Version
    0.55
    POSITIVE LOGITS
     sections
    0.70
     secciones
    0.70
    markets
    0.68
     Abschnitt
    0.64
     prêts
    0.63
    ară
    0.63
    段
    0.63
     section
    0.62
    리로
    0.62
    ע
    0.62
    Activations Density 0.036%

    No Known Activations