© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    উন
    0.72
    gherita
    0.65
    বাব
    0.64
     erinnert
    0.63
     Dolom
    0.62
    聒
    0.62
    imidazol
    0.62
    痙
    0.61
    entz
    0.61
    賑
    0.61
    POSITIVE LOGITS
     hidden
    5.15
    hidden
    4.76
     concealed
    4.60
     Hidden
    4.59
    Hidden
    4.59
    隐藏
    4.51
     hiding
    4.20
     escond
    3.99
     secret
    3.93
    隠
    3.90
    Activations Density 1.626%

    No Known Activations