© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    Ahmedia, town, disagree, time

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

    The neuron fires on interface label and navigational tokens (e.g. question_, answer, helpful, yes/no, arrow, keys, gallery) that mark UI elements or prompts.

    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
    í
    0.78
     ï
    0.77
    ori
    0.76
     telles
    0.75
    ogue
    0.73
     amaç
    0.71
    agen
    0.70
                   
    0.69
    }$
    0.69
    }$,
    0.68
    POSITIVE LOGITS
     dificult
    0.74
    𝚣
    0.73
     বিক্ষোভ
    0.73
     PublicKey
    0.73
    勮
    0.73
    mousePressed
    0.72
    Cx
    0.71
    われている
    0.71
    える
    0.70
     tomography
    0.69
    Activations Density 0.006%

    No Known Activations