© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10729
    Prev
    Next
    INDEX
    Explanations

    non-latin characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ici
    0.44
     AKA
    0.41
     bitcoin
    0.40
     R
    0.40
    }$
    0.39
     gradu
    0.39
    _
    0.39
    vari
    0.39
     Feder
    0.39
     લઈ
    0.39
    POSITIVE LOGITS
    ئیں۔
    0.49
     程序
    0.47
    ර්ශ
    0.46
    醅
    0.46
    জ্জনক
    0.46
     katol
    0.46
     要素
    0.46
     molasses
    0.46
    删除
    0.46
    രുവനന്തപുരം
    0.45
    Activations Density 0.007%

    No Known Activations