© 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. 79038
    Prev
    Next
    INDEX
    Explanations

    word followed by specific conjunction or punctuation

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

    Future Outlook, Allied Nations, Environmentalists, Degradation Problem

    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
     desl
    0.46
    ese
    0.45
    ils
    0.44
    usik
    0.44
     لج
    0.43
     Drake
    0.42
    វេល
    0.42
    :
    0.41
    éra
    0.41
    urs
    0.40
    POSITIVE LOGITS
    ेन्द्र
    0.59
     observations
    0.52
    忔
    0.51
    ეგისტრ
    0.49
    ଫ
    0.48
    𝗡
    0.48
    ੱਕ
    0.47
     வெளியே
    0.47
    データを
    0.47
    𝐊
    0.46
    Activations Density 0.002%

    No Known Activations