© 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-65K
    7. 30521
    Prev
    Next
    INDEX
    Explanations

    Tiber and history

    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_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
     nobleman
    0.52
     Nghi
    0.48
    enean
    0.47
     competitor
    0.45
     programmer
    0.45
     jeweler
    0.44
    온
    0.43
    an
    0.43
    lada
    0.43
     경쟁
    0.43
    POSITIVE LOGITS
     ми
    0.44
    層
    0.43
    casualties
    0.42
    层
    0.42
    ut
    0.41
     المست
    0.40
    এবং
    0.40
    うまく
    0.39
     στιγ
    0.39
    打破
    0.38
    Activations Density 0.010%

    No Known Activations