© 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. 48550
    Prev
    Next
    INDEX
    Explanations

    attempt to verb, ought to verb, previous to

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

    not or potential

    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
     suburbs
    0.33
     suburb
    0.33
     %>
    0.30
     the
    0.30
     esconder
    0.30
     la
    0.29
     indispens
    0.29
     leisure
    0.28
     C
    0.28
     el
    0.28
    POSITIVE LOGITS
     thereof
    0.44
    それに
    0.40
     того
    0.39
     সেখানেই
    0.39
    的那
    0.38
     тако
    0.38
     کی۔
    0.38
     उसमे
    0.38
    them
    0.38
    ॉइड
    0.38
    Activations Density 0.193%

    No Known Activations