© 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. 117632
    Prev
    Next
    INDEX
    Explanations

    vinyl designs

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

    future growth opportunities

    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
    代謝
    0.52
    勻
    0.49
    洁
    0.48
    姏
    0.48
    潔
    0.46
    竹
    0.46
    棟
    0.46
     César
    0.46
    櫓
    0.46
    లతో
    0.46
    POSITIVE LOGITS
    hlen
    0.54
     attribute
    0.48
     attenuation
    0.47
     u
    0.47
     attributes
    0.45
     aga
    0.45
     amplitudes
    0.45
     keperluan
    0.45
     اما
    0.45
     ater
    0.44
    Activations Density 0.001%

    No Known Activations