© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    followed by connecting words

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

    definition and explanation

    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
     гель
    0.37
    耠
    0.37
    䔧
    0.35
     waardoor
    0.35
     перспек
    0.35
     алге
    0.35
     جبکہ
    0.34
     памят
    0.34
    脷
    0.34
    といった
    0.34
    POSITIVE LOGITS
    之所以
    0.49
    只是
    0.40
     is
    0.39
    也
    0.38
     mainly
    0.36
     domine
    0.36
    的主
    0.36
    的是
    0.36
     often
    0.35
    有很多
    0.35
    Activations Density 0.044%

    No Known Activations