© 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. 33945
    Prev
    Next
    INDEX
    Explanations

    dumpster rental phone numbers

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

    multilingual context and code

    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
    ajout
    0.54
    dons
    0.52
    ☺
    0.49
    いろいろ
    0.49
     forças
    0.47
     propres
    0.46
    ３
    0.46
    言い
    0.46
    ராஜ்
    0.46
    小
    0.46
    POSITIVE LOGITS
     时
    0.52
     บริ
    0.50
     Frankfurt
    0.45
     เยอะ
    0.44
     Byl
    0.43
    াত্র
    0.43
     तब्
    0.43
     Data
    0.42
     σε
    0.42
     πολ
    0.42
    Activations Density 0.000%

    No Known Activations