© 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. 226128
    Prev
    Next
    INDEX
    Explanations

    magnifying and hydrocarbons

    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
     Urlaub
    0.51
    M
    0.49
    ي
    0.45
     vacations
    0.45
     وض
    0.44
     nuove
    0.42
    Yah
    0.42
    WD
    0.41
    Yoga
    0.41
    I
    0.41
    POSITIVE LOGITS
     magnifying
    0.45
     hydrocarbons
    0.44
     hydrocarbon
    0.44
    ()<<
    0.44
     ক্যাথোডে
    0.43
    thisobject
    0.43
    <unused1799>
    0.43
     méth
    0.42
     sanitizer
    0.42
     hydrostatic
    0.42
    Activations Density 0.001%

    No Known Activations