© 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. 124893
    Prev
    Next
    INDEX
    Explanations

    instruction

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

    explaining a situation or solution

    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
    ₺
    0.47
    !"
    0.45
     AML
    0.44
     Fridge
    0.44
    ţie
    0.44
     Brill
    0.44
     gjort
    0.44
    ﺧ
    0.43
    ção
    0.43
    çi
    0.43
    POSITIVE LOGITS
    کول
    0.55
    shortcuts
    0.50
    юнча
    0.49
    انت
    0.47
     querida
    0.46
    ونس
    0.46
    inputenc
    0.46
    コート
    0.44
    উদ
    0.44
    probable
    0.44
    Activations Density 0.001%

    No Known Activations