© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 536
    Prev
    Next
    INDEX
    Explanations

    etc. or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     unui
    1.30
    DETAILS
    1.30
    forth
    1.27
     каждого
    1.26
    ܕ
    1.26
    THEOREM
    1.26
     série
    1.25
     этой
    1.24
    :>
    1.23
    Actually
    1.22
    POSITIVE LOGITS
     etc
    1.75
     illetve
    1.55
     以及
    1.51
     kuten
    1.43
    omitempty
    1.42
     valamint
    1.41
    etc
    1.41
     ইত্যাদি
    1.31
     그리고
    1.25
     এমনকি
    1.23
    Activations Density 1.289%

    No Known Activations