© 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. 158409
    Prev
    Next
    INDEX
    Explanations

    counted manually

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

    break down, cut, stages

    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
     تشوف
    0.46
    ror
    0.46
    EMAN
    0.45
    htub
    0.44
    ("/");
    0.44
    ostiene
    0.43
    fulfill
    0.43
    的代码
    0.43
    keley
    0.43
     نشوف
    0.43
    POSITIVE LOGITS
     nuclear
    0.53
     verbal
    0.53
    h
    0.52
     nucleic
    0.51
     meiosis
    0.50
     IAEA
    0.50
     total
    0.49
     enigmatic
    0.48
    טן
    0.48
     immediate
    0.48
    Activations Density 0.002%

    No Known Activations