© 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
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2936
    Prev
    Next
    INDEX
    Explanations

    September 2021

    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
     Parse
    0.61
     suggested
    0.61
    ளிடம்
    0.60
    なた
    0.60
    이드
    0.60
    ᵏ
    0.59
    iceras
    0.57
    公
    0.56
    charCode
    0.56
    actose
    0.56
    POSITIVE LOGITS
    ud
    0.62
     lut
    0.62
    ruga
    0.61
    UTER
    0.61
    Elliott
    0.60
    ইল
    0.60
    oti
    0.58
    erm
    0.58
    マ
    0.58
    sailboat
    0.57
    Activations Density 0.204%

    No Known Activations