© 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. 53
    Prev
    Next
    INDEX
    Explanations

    yòng, bork, amah, k

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    L
    0.21
    as
    0.21
    F
    0.20
    I
    0.20
     During
    0.20
    G
    0.19
    R
    0.19
    in
    0.19
    Ltd
    0.18
    ਸ
    0.18
    POSITIVE LOGITS
     halluc
    0.17
     shivering
    0.17
     inextric
    0.16
     deut
    0.16
     manpower
    0.16
     hendak
    0.16
     kompet
    0.16
     suboptimal
    0.16
     overpower
    0.16
     abon
    0.15
    Activations Density 0.251%

    No Known Activations