© 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. 158649
    Prev
    Next
    INDEX
    Explanations

    risk death

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

    Multi-level marketing, literary techniques

    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
    见的
    0.46
    MenuBar
    0.46
    Curly
    0.43
    ে
    0.42
    เห็น
    0.42
     budding
    0.42
    กรณี
    0.42
    ลง
    0.41
    诛
    0.41
    ง
    0.41
    POSITIVE LOGITS
     retorna
    0.49
     desempen
    0.46
     csr
    0.44
     thereof
    0.44
     visok
    0.44
     nito
    0.43
     nimble
    0.43
     daarbij
    0.43
     agile
    0.43
     தேர்
    0.42
    Activations Density 0.000%

    No Known Activations