© 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. 24339
    Prev
    Next
    INDEX
    Explanations

    booking trips

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

    booking in advance

    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
     ჭ
    0.48
    ண்க
    0.45
    目で
    0.44
     pomiesz
    0.44
     வண
    0.43
    STRACT
    0.43
     বলিতে
    0.43
     পাইয়া
    0.42
    <0xB0>
    0.41
     গ্যাস
    0.40
    POSITIVE LOGITS
     booking
    0.65
     Booking
    0.63
     adventurous
    0.59
     booked
    0.57
    booking
    0.55
    booked
    0.55
    Booking
    0.54
     tourist
    0.53
     Adventure
    0.53
     Viator
    0.53
    Activations Density 0.036%

    No Known Activations