© 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. 181238
    Prev
    Next
    INDEX
    Explanations

    item is in the category

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

    explaining or understanding concepts

    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
    owali
    0.48
    1
    0.47
    ارق
    0.46
    INY
    0.45
    owal
    0.45
    જનો
    0.44
    ೭
    0.44
     Anthem
    0.44
    шою
    0.43
    ANGO
    0.43
    POSITIVE LOGITS
     कक्ष
    0.59
     बोर्ड
    0.50
    ி
    0.48
     whiteboard
    0.47
     sigmoid
    0.46
     incubation
    0.46
     शिक्षक
    0.45
     मिट्टी
    0.44
     porosity
    0.44
    rotation
    0.44
    Activations Density 0.002%

    No Known Activations