© 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. 128905
    Prev
    Next
    INDEX
    Explanations

    climate and temperature patterns

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

    climate science observations

    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
     风
    0.61
    堞
    0.57
    冻
    0.56
     Canva
    0.56
    风
    0.55
     domenica
    0.53
     Windy
    0.52
     sabato
    0.51
     Sabtu
    0.51
    节
    0.51
    POSITIVE LOGITS
    ERN
    0.49
    ARI
    0.47
    href
    0.47
     antisymmetric
    0.47
     asymmetry
    0.46
    semester
    0.46
    rl
    0.46
    PCA
    0.46
    ensemble
    0.45
    EM
    0.45
    Activations Density 0.038%

    No Known Activations