© 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. 251169
    Prev
    Next
    INDEX
    Explanations

    bespoke, derivatives, detail, Jerusalem

    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
    Opens
    0.42
     slipped
    0.41
     which
    0.41
    They
    0.41
     které
    0.41
    otypic
    0.40
     brutally
    0.40
    ä
    0.40
     które
    0.40
     ligger
    0.40
    POSITIVE LOGITS
    льбе
    0.51
    ኖር
    0.47
    ρκ
    0.47
     φωτογραφ
    0.47
     সংযুক্ত
    0.46
    슘
    0.45
     الخلي
    0.45
    λα
    0.44
     секрета
    0.44
    쥴
    0.44
    Activations Density 0.001%

    No Known Activations