© 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. 125972
    Prev
    Next
    INDEX
    Explanations

    legal terms and days

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

    Provide high-quality research

    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
     wholesalers
    0.55
     s
    0.49
     CSV
    0.49
     octopus
    0.48
     curves
    0.47
    PLOAD
    0.47
     Italians
    0.47
     diagrams
    0.46
     خمس
    0.46
     auraient
    0.46
    POSITIVE LOGITS
    ing
    0.53
    <unused345>
    0.52
    愛情
    0.49
    HomePage
    0.46
    MG
    0.46
    Restriction
    0.46
    Methylsulfanyl
    0.46
    Figura
    0.45
    List
    0.45
     محبت
    0.45
    Activations Density 0.003%

    No Known Activations