© 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. 157178
    Prev
    Next
    INDEX
    Explanations

    laughter, than, gas

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

    smaller, developing

    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
    nox
    0.52
    უკ
    0.51
    کز
    0.49
    ώρα
    0.46
    opes
    0.46
    ojis
    0.46
    ducted
    0.46
    є
    0.46
    ight
    0.46
    ipy
    0.46
    POSITIVE LOGITS
     expressly
    0.52
     stricken
    0.50
     ANOTHER
    0.50
     afflict
    0.48
     manifestly
    0.48
     nodig
    0.46
     concerted
    0.46
     apologizing
    0.45
     trembled
    0.45
     tornando
    0.45
    Activations Density 0.000%

    No Known Activations