© 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. 24707
    Prev
    Next
    INDEX
    Explanations

    leaves and foliage

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

    leaves change or fall

    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
     ejac
    0.53
     scrot
    0.49
    ۵
    0.49
    Მ
    0.48
     titolo
    0.47
     گویا
    0.46
     spermato
    0.46
     spermatozoa
    0.46
     vỏ
    0.46
    牦
    0.46
    POSITIVE LOGITS
     Leaves
    1.02
     Leaf
    0.96
     leaf
    0.91
    葉
    0.91
    Leaves
    0.91
     Leafs
    0.91
     leaves
    0.90
     leafs
    0.90
    leaf
    0.89
    Leaf
    0.89
    Activations Density 0.055%

    No Known Activations