© 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. 48001
    Prev
    Next
    INDEX
    Explanations

    agreement, line, disease

    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
    ИС
    0.52
    䡈
    0.50
    ి
    0.50
    рона
    0.49
     midwives
    0.49
    ва
    0.48
    uração
    0.48
    sdag
    0.48
     protocolo
    0.47
    ações
    0.47
    POSITIVE LOGITS
     Cool
    0.44
    겠
    0.43
     درمیان
    0.42
     lijn
    0.42
     linee
    0.42
     çarp
    0.41
    gimento
    0.41
     Lieblings
    0.41
    谎
    0.41
     dünya
    0.41
    Activations Density 0.001%

    No Known Activations