© 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. 260
    Prev
    Next
    INDEX
    Explanations

    Python __main__ block

    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
    an
    1.33
    at
    1.18
     call
    1.17
     industriel
    1.15
    ans
    1.14
    ani
    1.13
    @
    1.12
     element
    1.12
     per
    1.12
    ligt
    1.11
    POSITIVE LOGITS
    魅
    2.01
     Rite
    1.92
    ARRY
    1.84
     “‘
    1.79
    immie
    1.78
    <unused655>
    1.78
     做
    1.78
    <unused938>
    1.77
    SERVATION
    1.77
    Rite
    1.76
    Activations Density 0.031%

    No Known Activations