© 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. 49787
    Prev
    Next
    INDEX
    Explanations

    "owner who" pattern

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

    compound interest formula or specific terms

    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
    نسب
    0.41
     prä
    0.40
    }}{|
    0.40
    󠁧
    0.40
    鱈
    0.39
     notamment
    0.39
    捜
    0.38
    땄
    0.38
    codingPath
    0.37
     mâles
    0.37
    POSITIVE LOGITS
     Интер
    0.46
     Szt
    0.45
     నిజ
    0.44
    يء
    0.43
    好吧
    0.42
     time
    0.42
     Pandemic
    0.42
    ArgsConstructor
    0.41
     χρόνο
    0.40
    يزات
    0.40
    Activations Density 0.000%

    No Known Activations