© 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. 157183
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

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

    academic publishers and journals

    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
     вере
    0.46
     sett
    0.38
     katth
    0.38
    opher
    0.37
     मिठ
    0.37
     ड्रेस
    0.36
    觧
    0.36
     comprends
    0.36
     methylene
    0.36
    휠
    0.35
    POSITIVE LOGITS
     automating
    0.47
     arXiv
    0.47
     African
    0.45
     Republic
    0.44
    scalable
    0.41
     Kabupaten
    0.41
    African
    0.41
     выборах
    0.40
     Becker
    0.40
    BottomOf
    0.40
    Activations Density 0.076%

    No Known Activations