© 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. 97675
    Prev
    Next
    INDEX
    Explanations

    descriptions and outcomes

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

    descriptive terms and concepts

    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
    芎
    0.54
     türlü
    0.52
     छत्तीस
    0.51
     महाराष्ट्रा
    0.51
    TINGS
    0.50
    砒
    0.50
     التر
    0.50
     Aş
    0.49
    जरीवाल
    0.49
     Kamane
    0.48
    POSITIVE LOGITS
    '
    0.46
    ramiento
    0.45
     readable
    0.45
    <start_of_image>
    0.43
     bounds
    0.43
     passable
    0.41
    ussy
    0.40
    dimensional
    0.40
     цен
    0.40
     readability
    0.40
    Activations Density 0.001%

    No Known Activations