© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 90
    Prev
    Next
    INDEX
    Explanations

    eighty, fifty, numbers, war

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

    eighty or 88

    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_53_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
    <0xB3>
    0.79
     सात
    0.66
    Seven
    0.66
     Seven
    0.63
    seven
    0.63
    7
    0.63
     sieben
    0.63
    ７
    0.62
     seven
    0.62
    ၇
    0.58
    POSITIVE LOGITS
     Eighty
    0.52
     eighty
    0.52
     ocho
    0.49
    <0xB9>
    0.48
     fifty
    0.47
     Fifty
    0.44
    8
    0.44
    ¿
    0.44
    CodeableConcept
    0.43
    0.43
    Activations Density 0.441%

    No Known Activations