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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8357
    Prev
    Next
    INDEX
    Explanations

    creative writing and storytelling themes

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

    The neuron fires strongly on occurrences of the modal “may” (and related permission/possibility constructions).

    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_24_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
    Cu
    0.79
    W
    0.78
    DW
    0.77
    iums
    0.71
    R
    0.71
    IC
    0.71
    Dimension
    0.71
    ween
    0.70
    UV
    0.70
    ion
    0.70
    POSITIVE LOGITS
     fez
    0.89
     цилинд
    0.88
     календар
    0.78
     trigo
    0.77
    谩
    0.77
     tecido
    0.77
     отказыва
    0.76
     tenho
    0.75
     kal
    0.74
     imprensa
    0.74
    Activations Density 0.000%

    No Known Activations