© 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. 224106
    Prev
    Next
    INDEX
    Explanations

    felt until, designed Cambia, appointed standard

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

    high standard, collection, felt

    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
     sheds
    0.49
     jolie
    0.48
    _{\
    0.46
    вается
    0.45
    げ
    0.45
     ziet
    0.43
    searchText
    0.41
    XO
    0.41
    ጠቀም
    0.40
    しましたが
    0.40
    POSITIVE LOGITS
     Nevertheless
    0.55
     Imagine
    0.55
    棪
    0.53
     کریں۔
    0.47
     Sama
    0.46
    ताव
    0.46
     Mountains
    0.45
     Epistle
    0.45
    ము
    0.45
     Whatever
    0.45
    Activations Density 0.000%

    No Known Activations