© 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. 4159
    Prev
    Next
    INDEX
    Explanations

    specific entities and their descriptors

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

    specific topics and their subsequent details

    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
     詳細
    0.34
     significative
    0.34
    thebetter
    0.32
     بڑی
    0.32
    အပိုင်း
    0.31
     stoichiometric
    0.31
     دونوں
    0.31
    ष
    0.31
     pinpoint
    0.31
    หรือ
    0.31
    POSITIVE LOGITS
     murders
    0.34
     Education
    0.34
    -
    0.32
     boycot
    0.31
     education
    0.30
     Entrepreneurs
    0.29
     embargo
    0.29
     Entrepreneur
    0.29
     Vaccine
    0.29
     Pricing
    0.28
    Activations Density 0.454%

    No Known Activations