© 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. 11254
    Prev
    Next
    INDEX
    Explanations

    secret collaboration technologies

    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
    addena
    0.52
     воздей
    0.48
    псо
    0.46
    ༤
    0.44
    ו
    0.44
     взаимодей
    0.44
     сказа
    0.43
    точно
    0.43
     wholeheartedly
    0.42
    EDA
    0.42
    POSITIVE LOGITS
     api
    0.63
     miles
    0.50
     colonies
    0.50
     alcohol
    0.50
     It
    0.49
     radius
    0.49
     「
    0.48
     lobes
    0.48
     packages
    0.48
     pagi
    0.48
    Activations Density 0.001%

    No Known Activations