© 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. 203342
    Prev
    Next
    INDEX
    Explanations

    day trip

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

    open on, jugar con, keyboard to

    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
    ,
    0.47
     competition
    0.46
     H
    0.46
     appliance
    0.45
     weight
    0.43
     cylinder
    0.43
     applications
    0.43
    ’
    0.43
     G
    0.43
    competition
    0.42
    POSITIVE LOGITS
     डाउट्स
    0.54
    벅
    0.53
    댈
    0.53
    𒄷
    0.52
    ండ
    0.50
    嫚
    0.50
    翮
    0.50
    дак
    0.49
    頔
    0.48
    ల్లు
    0.48
    Activations Density 0.000%

    No Known Activations