© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1828
    Prev
    Next
    INDEX
    Explanations

    Rasa (Taste)

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

    The neuron flags content‐bearing, relatively rare or domain‐specific words (e.g. proper names, technical terms, and other high–information nouns/verbs).

    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
    <unused2172>
    0.96
     Grenoble
    0.96
    丈夫
    0.95
    状况
    0.93
    🖱
    0.93
    偶然
    0.92
     Burgund
    0.91
    <unused2125>
    0.91
    <unused2138>
    0.91
     transparen
    0.91
    POSITIVE LOGITS
    ла
    1.35
    u
    1.28
    h
    1.16
    al
    1.12
    y
    1.12
    ł
    1.10
    те
    1.09
    j
    1.09
    ing
    1.05
    у
    1.02
    Activations Density 6.997%

    No Known Activations