© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15797
    Prev
    Next
    INDEX
    Explanations

    identifying words followed by specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ช่วง
    0.39
    |.|.|
    0.38
    ]|
    0.38
    ...\...\
    0.38
     एखा
    0.38
     многое
    0.38
     ataupun
    0.37
    >|</
    0.37
    ありますが
    0.36
     sekal
    0.35
    POSITIVE LOGITS
    Чтобы
    0.41
    Rationale
    0.41
    ૬
    0.40
     değişken
    0.39
     upang
    0.38
     variabile
    0.38
    晞
    0.38
    remeno
    0.38
    Để
    0.37
    그래서
    0.37
    Activations Density 0.003%

    No Known Activations