© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    we or I

    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
    ,..
    1.53
    ,
    1.45
     somit
    1.30
    sequently
    1.30
    (
    1.27
    Hence
    1.25
    :
    1.25
    /
    1.25
    Consequently
    1.20
    ,—
    1.19
    POSITIVE LOGITS
     there
    1.34
     если
    1.30
     jeśli
    1.30
     according
    1.28
     despite
    1.28
     jika
    1.27
     según
    1.26
     якщо
    1.24
     if
    1.22
     given
    1.21
    Activations Density 0.477%

    No Known Activations