© 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-TRANSCODER-262K
    7. 15670
    Prev
    Next
    INDEX
    Explanations

    rain and wet weather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
     आईसी
    0.37
     ICE
    0.37
     Carlton
    0.37
     methylene
    0.36
     homophobic
    0.36
    ,&
    0.36
     SPM
    0.36
     ice
    0.35
    Ic
    0.35
     Ic
    0.35
    POSITIVE LOGITS
     rain
    1.05
    雨
    0.97
     Rain
    0.97
     rainy
    0.94
     lluvia
    0.94
    Rain
    0.92
     rains
    0.91
     raindrops
    0.89
     raining
    0.88
    ☔
    0.88
    Activations Density 0.056%

    No Known Activations