© 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. 99515
    Prev
    Next
    INDEX
    Explanations

    contact manufacturer

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

    started on port

    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
    rivez
    0.50
    верка
    0.47
    ，
    0.46
    如今
    0.44
    订
    0.44
     Engineer
    0.43
    ير
    0.43
    oria
    0.43
    每一次
    0.43
    正如
    0.43
    POSITIVE LOGITS
    ለመ
    0.48
    ing
    0.44
    চ্ছে
    0.43
    ในการ
    0.43
     เวลา
    0.43
    ain
    0.42
    subsec
    0.42
    ",[],"
    0.42
     tarp
    0.41
     grossesse
    0.41
    Activations Density 0.001%

    No Known Activations