© 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. 202428
    Prev
    Next
    INDEX
    Explanations

    can potentially enhance

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

    enhance or remember

    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
    йд
    0.44
    Brit
    0.44
    բ
    0.42
    சில்
    0.42
    кс
    0.42
     olig
    0.42
    예요
    0.42
    ள
    0.41
    ሻ
    0.41
     eukaryotes
    0.40
    POSITIVE LOGITS
     Cũng
    0.44
     వైర
    0.43
    هِ
    0.41
    issionais
    0.41
    嘴角
    0.41
    cities
    0.41
     Также
    0.41
     वाजिब
    0.41
     কট
    0.41
    álním
    0.41
    Activations Density 0.000%

    No Known Activations