© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8772
    Prev
    Next
    INDEX
    Explanations

    calling immediately

    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_16k_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
    icaria
    0.53
     capucha
    0.50
     incluida
    0.50
    mce
    0.50
     Cary
    0.48
    莉
    0.48
    addContainer
    0.46
     cortar
    0.46
    hadas
    0.45
    并在
    0.45
    POSITIVE LOGITS
    Popul
    0.50
     individual
    0.48
     thorough
    0.47
    United
    0.47
     ابتد
    0.46
     migratory
    0.45
    𝗧
    0.45
    UD
    0.44
     understandably
    0.44
     empirically
    0.44
    Activations Density 0.046%

    No Known Activations