© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9099
    Prev
    Next
    INDEX
    Explanations

    test cases and testing environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ../../../
    2.74
    Stainless
    2.56
    LE
    2.54
    alysis
    2.53
    обы
    2.45
    esri
    2.43
    onomics
    2.41
    갑
    2.40
    hydration
    2.40
    idated
    2.39
    POSITIVE LOGITS
    IamPermissions
    3.52
    imonials
    2.99
     cerc
    2.80
    aurants
    2.78
    aments
    2.67
    
    2.49
    OnUiThread
    2.49
     moi
    2.48
     souha
    2.46
     coba
    2.46
    Activations Density 0.136%

    No Known Activations