© 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. 16913
    Prev
    Next
    INDEX
    Explanations

    recovery, duplicate, elegant, purified, buzzing

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

    ways that, her nutritionist, next project

    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
    keeper
    0.39
    untamiento
    0.38
    ungo
    0.38
    גת
    0.38
    ັກ
    0.36
    뀝
    0.36
    kala
    0.36
    keepers
    0.35
    蓥
    0.35
     círculo
    0.35
    POSITIVE LOGITS
     towed
    0.42
     SUBSCRIBE
    0.41
     HIF
    0.39
     スタッドレスタイヤ
    0.38
     Morrison
    0.36
     STL
    0.36
     TO
    0.36
     Comparison
    0.36
     subscribed
    0.36
    ించడానికి
    0.36
    Activations Density 0.015%

    No Known Activations