© 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. 254286
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ей
    0.48
     arrang
    0.47
     Mustangs
    0.46
    蒺
    0.45
    িস্ট
    0.44
    FindAction
    0.43
    ﻪ
    0.43
    था
    0.43
    ፍት
    0.43
    гээ
    0.42
    POSITIVE LOGITS
     bénéficier
    0.55
     モダン
    0.49
    pooled
    0.47
     カ
    0.46
     vérifier
    0.46
    <unused2199>
    0.46
    AI
    0.45
     例えば
    0.45
     中古
    0.45
     オール
    0.44
    Activations Density 0.001%

    No Known Activations