© 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. 131038
    Prev
    Next
    INDEX
    Explanations

    county, island, crisis, adventure

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

    multimedia categories

    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
     दुनियाभर
    0.59
    Easing
    0.53
     परस्मैपदी
    0.51
     Egy
    0.49
     Martyrs
    0.49
    icited
    0.49
    愆
    0.48
    acidad
    0.48
    Egyptian
    0.47
     स्त्रियों
    0.47
    POSITIVE LOGITS
    డం
    0.46
    8
    0.45
    ı
    0.45
    ა
    0.44
    7
    0.43
     convers
    0.43
     වේ
    0.43
     adversely
    0.42
     imó
    0.42
    廣告
    0.42
    Activations Density 0.000%

    No Known Activations