© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 35725
    Prev
    Next
    INDEX
    Explanations

    water temperature and act

    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_31_width_65k_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
     اربع
    0.55
     cili
    0.51
    <unused734>
    0.51
    ا۔
    0.50
     bialgebras
    0.50
    Paxos
    0.50
    ン
    0.50
    ambo
    0.49
     няколко
    0.49
     geopol
    0.49
    POSITIVE LOGITS
    uality
    0.51
    _
    0.49
    end
    0.48
    '
    0.48
    ↵
    0.47
     produc
    0.45
     $(
    0.44
    ↵↵↵
    0.43
    ieved
    0.41
    iculos
    0.41
    Activations Density 0.012%

    No Known Activations