© 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. 298
    Prev
    Next
    INDEX
    Explanations

    python dunder methods

    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
     BusABC
    3.02
     Гиндзё
    3.02
    𒌜
    3.00
    𒂟
    3.00
    𒌐
    3.00
    𒀖
    2.99
    𒐕
    2.98
    𒊨
    2.98
    𒈣
    2.97
    BlackSholes
    2.96
    POSITIVE LOGITS
    s
    3.17
    e
    2.63
    t
    2.51
    y
    2.32
    l
    2.26
    o
    2.21
    a
    2.19
    i
    2.12
    n
    2.09
    er
    2.07
    Activations Density 17.479%

    No Known Activations