© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13058
    Prev
    Next
    INDEX
    Explanations

    and connectors

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

    the presence of numerical values expressed with decimal points (floating-point numbers).

    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
    他們
    0.73
    GREAT
    0.73
    レストラン
    0.71
    Celebr
    0.71
     genieten
    0.70
    𝗰
    0.70
    兒子
    0.70
    Gift
    0.70
    Restaurants
    0.70
    𝗽
    0.69
    POSITIVE LOGITS
     (
    0.87
     the
    0.78
     based
    0.76
     sequential
    0.75
     occurs
    0.73
     invariant
    0.72
     (=
    0.72
     or
    0.70
     relatively
    0.70
     scalar
    0.69
    Activations Density 0.093%

    No Known Activations