© 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. 114458
    Prev
    Next
    INDEX
    Explanations

    radar

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

    natural resilience

    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
     wymag
    0.48
     thorny
    0.46
     einigen
    0.45
     ಕೆಲವು
    0.43
    lemagne
    0.43
     "${
    0.43
    /${
    0.42
     teilweise
    0.42
     zdję
    0.42
    ঞ্চল্য
    0.42
    POSITIVE LOGITS
    所有的
    0.50
    া
    0.43
    H
    0.43
     acetylene
    0.42
    ACE
    0.41
    ου
    0.41
    KB
    0.41
    ầy
    0.40
    JAVA
    0.40
    ત્ર
    0.40
    Activations Density 0.009%

    No Known Activations