© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2105
    Prev
    Next
    INDEX
    Explanations

    descriptive words followed by conjunctions

    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_40_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
     bicovariant
    0.30
     '.',
    0.30
     resized
    0.30
     {\
    0.29
     genannten
    0.29
     ஹோ
    0.29
     жөн
    0.29
    üllen
    0.29
     greater
    0.28
    єю
    0.28
    POSITIVE LOGITS
     للغاية
    0.64
     enough
    0.59
     और
    0.58
     but
    0.55
     và
    0.55
     आणि
    0.55
     demais
    0.55
     и
    0.55
     અને
    0.54
    และ
    0.54
    Activations Density 1.410%

    No Known Activations