© 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. 162002
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    historical and geographical descriptions

    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
     „
    0.44
     ingot
    0.43
     wicket
    0.42
     ايش
    0.41
     loko
    0.41
    rack
    0.40
     conspicuously
    0.39
     [/
    0.39
     serviceable
    0.38
     ‘
    0.38
    POSITIVE LOGITS
    产品
    0.57
    製品
    0.53
    蝮
    0.48
    제품
    0.47
    安全
    0.47
    ين
    0.46
    产品的
    0.46
    Greece
    0.46
    攺
    0.45
     luglio
    0.45
    Activations Density 0.001%

    No Known Activations