© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    reply to

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

    reply to

    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
    Calibration
    0.47
     sépt
    0.46
    િ
    0.46
     Calibration
    0.44
    Yi
    0.44
    Configuration
    0.43
    к
    0.43
    娩
    0.42
    ём
    0.42
     Configuration
    0.42
    POSITIVE LOGITS
    ని
    0.53
    ನ
    0.47
    nol
    0.46
    nings
    0.44
    eppo
    0.44
    ný
    0.44
    महल
    0.44
    nar
    0.44
     придется
    0.44
    nama
    0.43
    Activations Density 0.009%

    No Known Activations