© 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. 5172
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase

    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
     
    0.88
    s
    0.72
     feet
    0.63
     suffices
    0.61
     C
    0.59
     assign
    0.57
     loss
    0.56
     sizes
    0.55
     potassium
    0.55
     land
    0.55
    POSITIVE LOGITS
    på
    0.64
    __."
    0.63
    ين
    0.62
    bbero
    0.61
    omist
    0.61
    importanza
    0.60
    éducation
    0.60
    豊かな
    0.60
    STAGE
    0.59
    enapi
    0.59
    Activations Density 10.279%

    No Known Activations