© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135894
    Prev
    Next
    INDEX
    Explanations

    watery terms

    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
     десяти
    0.52
    十年
    0.49
    百年
    0.43
    ĸ
    0.43
     عشر
    0.42
     conduire
    0.40
     vuos
    0.40
    徙
    0.39
     Оста
    0.39
     maanden
    0.39
    POSITIVE LOGITS
     ICD
    0.43
     radial
    0.42
     IDs
    0.40
     indices
    0.39
     LU
    0.38
    撕
    0.38
     diffusion
    0.38
    వచ్చు
    0.36
    ids
    0.36
     phía
    0.36
    Activations Density 0.001%

    No Known Activations