© 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. 138362
    Prev
    Next
    INDEX
    Explanations

    foreign language or cultural concepts

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

    biblical fault light Bible

    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
     интернете
    0.43
    ंता
    0.42
    ंसा
    0.41
     advertisements
    0.41
    떼
    0.41
    ма
    0.40
     campaigning
    0.40
     advertisement
    0.40
     Indien
    0.39
    ماً
    0.39
    POSITIVE LOGITS
     ರಿಂದ
    0.55
    ătur
    0.49
    gris
    0.48
    deg
    0.48
     ର
    0.47
    cycl
    0.47
    éroport
    0.46
    cultural
    0.46
    都沒有
    0.46
    發生
    0.46
    Activations Density 0.001%

    No Known Activations