© 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. 16-GEMMASCOPE-2-RES-65K
    7. 433
    Prev
    Next
    INDEX
    Explanations

    nexus point

    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_16_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
    ;
    0.51
     orthonormal
    0.50
     expression
    0.49
    The
    0.48
    를
    0.46
     restraint
    0.46
     recursion
    0.46
     loss
    0.46
     phot
    0.45
     magnification
    0.45
    POSITIVE LOGITS
     هاي
    0.59
    })$;
    0.55
     mať
    0.55
    larınız
    0.53
    WithFieldContext
    0.52
    inicial
    0.52
     selecionar
    0.52
     Από
    0.52
    lı
    0.51
    larımız
    0.51
    Activations Density 0.000%

    No Known Activations