© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136292
    Prev
    Next
    INDEX
    Explanations

    security, improvement, Airport

    np_acts-logits-general · gemini-2.5-flash-lite

    planning, translating, awful, if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    气体
    0.52
    汽
    0.51
    Spinner
    0.46
     學
    0.46
    Purple
    0.45
    Mq
    0.44
     نفر
    0.44
    Https
    0.44
    煉
    0.44
    ﹚
    0.43
    POSITIVE LOGITS
     fitting
    0.52
     certification
    0.48
     Hilbert
    0.47
     posting
    0.46
     ELISA
    0.46
     bribery
    0.45
    esthetics
    0.45
     Win
    0.45
     fortification
    0.44
     hard
    0.43
    Activations Density 0.000%

    No Known Activations