© 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-16K
    7. 11690
    Prev
    Next
    INDEX
    Explanations

    number of reviews

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

    Google reviews and ratings

    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_16k_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
    想想
    0.43
    😎
    0.39
    )+'
    0.38
    앗
    0.38
     Iss
    0.38
    😏
    0.37
    😒
    0.37
    ◘
    0.37
     அரு
    0.37
    itió
    0.36
    POSITIVE LOGITS
    複合
    0.45
    akumar
    0.45
     Haemat
    0.45
     পাঁচটি
    0.44
    оні
    0.44
     resonators
    0.43
    に基づ
    0.43
    rens
    0.42
     ทีม
    0.41
    ontinuous
    0.41
    Activations Density 0.009%

    No Known Activations