© 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. 23199
    Prev
    Next
    INDEX
    Explanations

    date stamps

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

    structured knowledge bases

    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
     insufficient
    0.41
    縣
    0.40
    كس
    0.39
     routine
    0.39
    libraries
    0.38
    erne
    0.37
    shipping
    0.37
     theses
    0.36
    SECONDARY
    0.36
    <!
    0.36
    POSITIVE LOGITS
     Wikispecies
    0.52
     enlace
    0.51
     đất
    0.47
     সম্ভবনা
    0.47
     siker
    0.47
    medallas
    0.47
     alturas
    0.47
     Vikipedi
    0.47
     શક
    0.46
     পাঁ
    0.46
    Activations Density 0.000%

    No Known Activations