© 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. 52848
    Prev
    Next
    INDEX
    Explanations

    words ending in ing

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

    output skin

    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
    น
    0.51
    ת
    0.50
    ע
    0.49
    לט
    0.47
     זי
    0.46
    ז
    0.46
    ட்க
    0.46
    ד
    0.46
    ל
    0.45
    求
    0.45
    POSITIVE LOGITS
     cryptography
    0.53
     esports
    0.48
     topologies
    0.48
    topology
    0.48
     tournament
    0.47
     batsman
    0.47
     invariants
    0.47
     somatic
    0.46
     فوتب
    0.46
     जवान
    0.46
    Activations Density 0.000%

    No Known Activations