© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8072
    Prev
    Next
    INDEX
    Explanations

    test 2 / July

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

    splitting words or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    टीएस
    0.50
    STRING
    0.45
     SUBSTIT
    0.45
     glial
    0.45
    脷
    0.45
    AKER
    0.44
    rocyte
    0.44
    ALSE
    0.43
     MATERIAL
    0.43
    ungal
    0.43
    POSITIVE LOGITS
    hit
    0.52
    hits
    0.50
    ᒫ
    0.50
    Amazon
    0.47
    FlowNode
    0.47
    categorie
    0.46
    出來
    0.46
    Hamilton
    0.46
    Birmingham
    0.46
    咣
    0.46
    Activations Density 0.000%

    No Known Activations