© 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. 172962
    Prev
    Next
    INDEX
    Explanations

    sell fast property

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

    language and depends

    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
    բ
    0.49
    ținut
    0.46
    าร์
    0.46
    庆
    0.45
     PACE
    0.45
     réseau
    0.45
    IDER
    0.45
     dată
    0.45
    ţ
    0.44
     চেয়ার
    0.44
    POSITIVE LOGITS
     ماحول
    0.48
    ండ్
    0.46
     జా
    0.46
     schoolchildren
    0.46
    лиги
    0.44
     locals
    0.43
     अवधि
    0.42
     ក
    0.42
     గ్రామ
    0.42
     языка
    0.42
    Activations Density 0.000%

    No Known Activations