© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51763
    Prev
    Next
    INDEX
    Explanations

    want to know

    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_40_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
     daje
    0.44
     arrêter
    0.43
     endeavoured
    0.42
     tarz
    0.42
    翛
    0.41
     почита
    0.41
     makarna
    0.40
     davantage
    0.40
     encountered
    0.39
     koristi
    0.39
    POSITIVE LOGITS
     Learn
    0.47
    Learn
    0.44
    berra
    0.41
    IFT
    0.41
    ామని
    0.39
    inghouse
    0.39
    হাকে
    0.39
     learn
    0.38
    >/</
    0.38
    全て
    0.38
    Activations Density 0.010%

    No Known Activations