© 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. 25329
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly quantities

    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
     lysosomes
    0.50
    к
    0.49
    هِ
    0.49
     sodio
    0.49
     antiserum
    0.49
     schm
    0.49
     gerek
    0.48
     vix
    0.48
     invoc
    0.48
     disapp
    0.47
    POSITIVE LOGITS
    five
    0.66
     दरम्यान
    0.59
    four
    0.55
    six
    0.55
    中に
    0.51
    hidden
    0.47
    俩
    0.47
    均为
    0.47
    罚
    0.47
    grid
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.