© 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. 109420
    Prev
    Next
    INDEX
    Explanations

    resources and limitations

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

    following punctuation

    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
     bajos
    0.50
     james
    0.50
    ENDS
    0.48
     $\
    0.47
     iga
    0.46
     and
    0.46
     subjekt
    0.46
     és
    0.45
     privado
    0.45
    3
    0.44
    POSITIVE LOGITS
    Gosudarstvennyj
    0.47
    ılması
    0.47
    ডিং
    0.46
     សូម
    0.46
     अनो
    0.46
     આપણે
    0.45
     તેણીએ
    0.45
     গ্রন্
    0.44
    勹
    0.43
     WindowStateType
    0.43
    Activations Density 0.000%

    No Known Activations