Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47745
    Prev
    Next
    INDEX
    Explanations

    publicly available, violence or, a long, over X, child endangerment

    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_65k_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
     coined
    1.12
    dtypes
    1.10
     stepped
    1.08
     VPD
    1.08
     процессов
    1.05
     côté
    1.02
     closely
    1.02
    ت
    0.99
     stranger
    0.95
     unnamed
    0.95
    POSITIVE LOGITS
    arono
    1.32
    in
    1.28
    িত
    1.24
    𝘵
    1.15
    यों
    1.14
     analges
    1.13
     Scalar
    1.12
    ্রে
    1.12
     fg
    1.11
     Cancel
    1.10
    Activations Density 0.001%

    No Known Activations