© 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. 226
    Prev
    Next
    INDEX
    Explanations

    great positive evaluations

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

    The neuron detects enthusiastic praise and positive evaluative language (e.g. compliments and glowing adjectives).

    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
    PILE
    0.40
    0.40
    dbo
    0.40
    บาง
    0.39
    PCI
    0.38
    0.38
    特定の
    0.38
    0.38
    ://
    0.37
    Università
    0.37
    POSITIVE LOGITS
     👍
    0.59
     mooie
    0.58
    👍
    0.58
     güzel
    0.55
     mooi
    0.55
     schön
    0.53
     идея
    0.53
     teamwork
    0.52
     camaraderie
    0.51
     artwork
    0.51
    Activations Density 0.218%

    No Known Activations