© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132026
    Prev
    Next
    INDEX
    Explanations

    pH or stability, complex flow, disease, specific models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excretion
    0.44
     acquires
    0.43
     গ্রহণের
    0.42
     acquisitions
    0.41
     exogenous
    0.40
    intérêt
    0.40
    擇
    0.40
    Disposition
    0.40
    acquired
    0.40
     acquisition
    0.39
    POSITIVE LOGITS
    uuml
    0.42
    ллі
    0.41
    టికి
    0.41
    inic
    0.39
     Without
    0.39
    𝒊
    0.38
     sent
    0.37
    ennie
    0.37
     Complexity
    0.37
    యిత
    0.37
    Activations Density 0.000%

    No Known Activations