© 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. 20250
    Prev
    Next
    INDEX
    Explanations

    phrase completion

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

    explore without

    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
    ；
    0.42
     まず
    0.42
    ၊
    0.42
     ,
    0.41
    త్రిక
    0.41
     bày
    0.41
    ignation
    0.40
    ٬
    0.40
    ．
    0.40
     lop
    0.39
    POSITIVE LOGITS
    Efficiency
    0.53
     sensores
    0.47
     bragging
    0.46
     पटाखे
    0.46
    Charge
    0.45
    证据
    0.45
    赠
    0.45
    וי
    0.44
    ँसी
    0.44
     Geräte
    0.44
    Activations Density 0.000%

    No Known Activations