© 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. 26751
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common words

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

    through the

    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
    合金
    0.52
     IntegerValue
    0.51
    洟
    0.49
    力
    0.48
    含量
    0.47
    皖
    0.47
     Gord
    0.44
    虚
    0.44
     言
    0.43
     力
    0.43
    POSITIVE LOGITS
    व्यक्ति
    0.48
     dusk
    0.48
     deviations
    0.47
     Joo
    0.47
     contests
    0.46
     doubts
    0.46
     unlimited
    0.46
    idelberg
    0.46
     alignments
    0.45
     minh
    0.45
    Activations Density 0.000%

    No Known Activations