© 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. 41416
    Prev
    Next
    INDEX
    Explanations

    tagged items

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

    specializes in or familiar with

    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
    ദ്
    0.45
    hob
    0.43
    Ｆ
    0.43
    کرات
    0.43
    ্কৃত
    0.42
    lains
    0.42
     scritto
    0.40
    elajaran
    0.40
    دارة
    0.40
     transt
    0.39
    POSITIVE LOGITS
     सामुदायिक
    0.53
     কয়েক
    0.48
     ज़रूर
    0.46
    噰
    0.46
    次回
    0.45
    態
    0.45
     오랜
    0.45
    }):=\
    0.45
    राम
    0.45
     أول
    0.45
    Activations Density 0.000%

    No Known Activations