© 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. 41-GEMMASCOPE-2-RES-65K
    4. 15430
    Prev
    Next
    INDEX
    Explanations

    Code, languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    檚
    0.47
    amerika
    0.43
    र्यंत
    0.43
    castellan
    0.43
    বিষ্য
    0.42
    shoring
    0.42
    bestroute
    0.41
    ckiej
    0.40
    ният
    0.40
    altungs
    0.40
    POSITIVE LOGITS
     this
    0.44
     void
    0.43
     è
    0.43
     validate
    0.42
     which
    0.42
    -
    0.42
     any
    0.41
     it
    0.41
     {
    0.41
     String
    0.40
    Activations Density 0.001%

    No Known Activations