© 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. 8068
    Prev
    Next
    INDEX
    Explanations

    progress and change

    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
     an
    0.44
     cryptographic
    0.43
     country
    0.42
     infer
    0.42
    ฆ
    0.41
    ม
    0.41
     பொருள்
    0.41
     a
    0.40
     ا
    0.40
     deliver
    0.40
    POSITIVE LOGITS
     हेल्दी
    0.57
     artık
    0.53
     embarazada
    0.53
     weaning
    0.52
     élim
    0.51
     ஆரம்பித்த
    0.51
     helemaal
    0.50
     commencé
    0.50
     soreness
    0.50
    allaitement
    0.49
    Activations Density 0.036%

    No Known Activations