© 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-16K
    7. 12974
    Prev
    Next
    INDEX
    Explanations

    keywords after tagged

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

    understandable systems or languages

    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_16k_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
    Ар
    0.51
     recomendamos
    0.50
     NONINFRINGEMENT
    0.49
    Ч
    0.48
    Д
    0.47
    Архі
    0.47
    Ш
    0.46
    グ
    0.46
    čnog
    0.45
     определенных
    0.45
    POSITIVE LOGITS
    lude
    0.51
    virus
    0.50
     homepage
    0.48
    obia
    0.46
    igree
    0.46
    nurse
    0.46
     timeline
    0.46
    timeline
    0.46
     could
    0.45
    school
    0.45
    Activations Density 0.011%

    No Known Activations