© 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-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7607
    Prev
    Next
    INDEX
    Explanations

    Names followed by punctuation or missed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steroids
    0.36
     anabolic
    0.35
    ו
    0.34
    fowl
    0.34
    ദ്ദേ
    0.33
     handgun
    0.33
     obtains
    0.32
     edifice
    0.32
    y
    0.32
     informacije
    0.31
    POSITIVE LOGITS
    .
    0.35
    ρα
    0.34
    ра
    0.34
    adding
    0.33
    ira
    0.33
    empl
    0.32
    ầng
    0.32
    oto
    0.31
    app
    0.31
    ila
    0.31
    Activations Density 0.082%

    No Known Activations