© 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. 52681
    Prev
    Next
    INDEX
    Explanations

    start phrase with common words

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

    english and other languages

    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
     sentimos
    0.46
     रफी
    0.46
    在我们
    0.46
    मारा
    0.46
    、（
    0.44
    觊
    0.44
    簌
    0.44
     imagina
    0.43
    بيه
    0.42
    䒴
    0.42
    POSITIVE LOGITS
     jų
    0.44
    fclose
    0.42
     ਸੁ
    0.42
     już
    0.41
     স
    0.41
     मोठे
    0.40
     ĝi
    0.40
     אי
    0.40
    BOOLE
    0.40
    既に
    0.39
    Activations Density 0.000%

    No Known Activations