© 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. 33778
    Prev
    Next
    INDEX
    Explanations

    travel costs

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

    certain context</b> (then) or specific terms

    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
    שו
    0.44
    Mur
    0.40
     المث
    0.39
    ద్దు
    0.39
     progn
    0.39
    పర
    0.39
     best
    0.38
    \%
    0.38
    IOS
    0.37
    ഖ
    0.37
    POSITIVE LOGITS
     outras
    0.47
     পর্যবেক্ষণ
    0.46
     খাদ্য
    0.46
     eten
    0.46
     Ă
    0.46
     खाली
    0.44
     uptick
    0.44
     ダイニング
    0.44
     textured
    0.43
     rewire
    0.43
    Activations Density 0.000%

    No Known Activations