© 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. 220332
    Prev
    Next
    INDEX
    Explanations

    scheduled for

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

    phrase and word pairings

    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
    សុ
    0.46
    結合
    0.45
    滸
    0.44
    睏
    0.43
    轶
    0.42
    以色列
    0.41
     पर्य
    0.41
    ա
    0.41
    薩
    0.41
    浥
    0.41
    POSITIVE LOGITS
     میدان
    0.49
    রাও
    0.48
    riente
    0.46
     लखनऊ
    0.46
     [](
    0.46
     Betrieb
    0.45
     DIVISION
    0.45
     mando
    0.45
     convoy
    0.44
     helicopter
    0.43
    Activations Density 0.000%

    No Known Activations