© 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. 128748
    Prev
    Next
    INDEX
    Explanations

    shrinking

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

    shrunken man

    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
    ul
    0.49
    is
    0.45
     アー
    0.45
    Ends
    0.43
     कोट
    0.41
     Ends
    0.41
    ்டு
    0.40
    ṭ
    0.40
    on
    0.40
    Owner
    0.39
    POSITIVE LOGITS
    shrink
    0.83
     shrink
    0.77
     shrunk
    0.75
     shrank
    0.75
     shrinking
    0.70
     shrinks
    0.70
     shrinkage
    0.68
     сокра
    0.64
     rétréci
    0.63
    缩
    0.63
    Activations Density 0.015%

    No Known Activations