© 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. 162932
    Prev
    Next
    INDEX
    Explanations

    we to, we prefer

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

    specific phrases and acronyms

    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
     இறுதியில்
    0.49
     இறு
    0.49
    하거나
    0.48
     և
    0.47
     শেষের
    0.47
    entropic
    0.46
    ajout
    0.46
     இறுதி
    0.46
     வெறு
    0.46
    sole
    0.45
    POSITIVE LOGITS
     of
    0.44
     erg
    0.42
     Grac
    0.42
     verily
    0.41
     fag
    0.40
     intrinsically
    0.40
    ucine
    0.40
    <0xE2>
    0.39
     was
    0.39
     Cres
    0.39
    Activations Density 0.001%

    No Known Activations