© 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. 35013
    Prev
    Next
    INDEX
    Explanations

    mixed languages and topics

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

    by followed by word

    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
    =
    0.50
    :,
    0.45
     =
    0.45
    threaded
    0.43
    ]。
    0.43
    :(
    0.42
    ўся
    0.42
     =,
    0.42
    াঃ
    0.42
    чков
    0.42
    POSITIVE LOGITS
     संदेह
    0.44
     ক্ষুধা
    0.41
    dok
    0.39
     سلط
    0.39
     Techn
    0.39
     पैटर्न
    0.38
    鳎
    0.38
     Estimated
    0.37
     शु
    0.37
    ૧
    0.37
    Activations Density 0.002%

    No Known Activations