© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81590
    Prev
    Next
    INDEX
    Explanations

    pattern-based questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ur
    0.49
    呜
    0.48
     zmian
    0.44
     ziel
    0.43
    崱
    0.43
     змін
    0.43
     paese
    0.43
     অন্তর্
    0.42
     我們
    0.42
    ेन
    0.42
    POSITIVE LOGITS
     poids
    0.42
    centered
    0.42
     appreciable
    0.40
    rockets
    0.40
    ্ল্ড
    0.40
    ностью
    0.40
    H
    0.40
    prox
    0.40
     functioned
    0.40
     pice
    0.39
    Activations Density 0.002%

    No Known Activations