© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233060
    Prev
    Next
    INDEX
    Explanations

    specific phrases

    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
     pasar
    0.52
    <0x80>
    0.50
     panas
    0.48
    <h2>
    0.47
    針
    0.46
    ד
    0.46
    𝗅
    0.45
    oriale
    0.44
    d
    0.44
     regla
    0.44
    POSITIVE LOGITS
     HashTable
    0.50
     آنے
    0.47
    猕
    0.46
    㖑
    0.46
    䓶
    0.46
     Founded
    0.46
     بہانہ
    0.45
     ভাইস
    0.45
     খ্র
    0.44
    btnAdd
    0.44
    Activations Density 0.000%

    No Known Activations