© 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. 4173
    Prev
    Next
    INDEX
    Explanations

    places of interest

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

    The neuron activates on words referring to social support or assistance services (e.g. “interacting,” “Graduation,” “shelter”).

    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
    0
    0.56
    5
    0.56
    4
    0.54
    9
    0.53
     selatan
    0.53
    6
    0.52
     holotype
    0.52
    8
    0.52
    7
    0.52
     इसे
    0.51
    POSITIVE LOGITS
     animals
    0.84
     handicrafts
    0.83
     animais
    0.80
     churches
    0.80
     zoos
    0.76
     racetr
    0.76
     cooperatives
    0.75
     museums
    0.75
     ወይም
    0.75
     hewan
    0.74
    Activations Density 0.148%

    No Known Activations