© 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. 160062
    Prev
    Next
    INDEX
    Explanations

    travel guide information

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

    understanding values

    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
    릭
    0.55
    ین
    0.54
    情况下
    0.53
    tsi
    0.52
    ától
    0.51
    ád
    0.49
     assuré
    0.49
    िद
    0.48
    נה
    0.48
    tion
    0.47
    POSITIVE LOGITS
     photoshoot
    0.50
     paddle
    0.49
     backpack
    0.48
     blowout
    0.48
     %
    0.48
     download
    0.48
     blog
    0.48
     challenge
    0.48
     exploit
    0.47
     paddles
    0.46
    Activations Density 0.002%

    No Known Activations