© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2174
    Prev
    Next
    INDEX
    Explanations

    academic papers and research content

    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
    rosion
    0.55
    t
    0.54
     C
    0.50
     andolan
    0.49
     arrhythmias
    0.48
     k
    0.47
     a
    0.46
     chico
    0.46
     нәрсә
    0.46
    ä
    0.46
    POSITIVE LOGITS
    Об
    0.54
    Пре
    0.54
    論文
    0.52
     scientifiques
    0.51
    Particle
    0.50
    व
    0.50
    При
    0.49
    Academic
    0.49
    Ри
    0.49
    एम
    0.49
    Activations Density 0.164%

    No Known Activations