© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    army, Tweet, porn, Host

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

    The neuron fires on proper names, brand or product titles, and other named-entity tokens.

    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
    thisTrack
    0.44
    第壹百
    0.44
    朹
    0.44
    眅
    0.42
    ដែ
    0.42
     underserved
    0.42
     reputed
    0.41
     untapped
    0.40
     Agencia
    0.40
     جسے
    0.39
    POSITIVE LOGITS
    K
    0.55
     AND
    0.53
    /
    0.52
    M
    0.51
    -
    0.49
    S
    0.48
    X
    0.48
     से
    0.47
    +
    0.47
    PS
    0.45
    Activations Density 2.436%

    No Known Activations