© 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. 8629
    Prev
    Next
    INDEX
    Explanations

    Spoon

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

    mathematical context

    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
    뇰
    0.28
    嫄
    0.26
    ⵎ
    0.25
     했
    0.25
    菈
    0.25
     philanth
    0.24
     brug
    0.24
     vermiş
    0.24
    纷
    0.24
    ﻜ
    0.24
    POSITIVE LOGITS
    ii
    0.33
     In
    0.32
    ed
    0.31
    ist
    0.31
    yl
    0.31
     Thus
    0.31
    ee
    0.30
     According
    0.30
    ile
    0.29
     Assuming
    0.29
    Activations Density 0.083%

    No Known Activations