© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8713
    Prev
    Next
    INDEX
    Explanations

    code blocks and tags

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to standalone numeric tokens containing decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    getitem
    0.54
    tanh
    0.54
    ismatch
    0.52
    assertEquals
    0.52
    imiter
    0.52
    argmax
    0.52
     }$
    0.51
    incorrect
    0.51
     }-
    0.50
    cursor
    0.49
    POSITIVE LOGITS
     meski
    0.58
     monetize
    0.54
     embora
    0.53
     consci
    0.51
     meskipun
    0.51
     Meskipun
    0.50
     förs
    0.48
     univers
    0.47
     although
    0.47
     감사합니다
    0.47
    Activations Density 0.000%

    No Known Activations