© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    dollar ranges and estimates

    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
    5
    1.10
    8
    1.05
    7
    1.02
    9
    1.02
    4
    0.95
    3
    0.95
    6
    0.95
    0
    0.95
    ½
    0.92
    2
    0.89
    POSITIVE LOGITS
     Olimpi
    0.63
     Kennt
    0.61
     átomos
    0.60
     synchrotron
    0.59
     Millions
    0.59
     milhares
    0.59
     millions
    0.58
     mutations
    0.58
    万美元
    0.58
     mitosis
    0.56
    Activations Density 0.138%

    No Known Activations