© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127384
    Prev
    Next
    INDEX
    Explanations

    phrases modifying nouns describing actions

    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
     BMW
    0.49
    魏
    0.49
     Windows
    0.47
    當
    0.46
     Wednesday
    0.46
    部
    0.45
     Wolfgang
    0.45
     on
    0.45
     Johann
    0.44
     Volkswagen
    0.44
    POSITIVE LOGITS
    effici
    0.54
    ignation
    0.53
     individualism
    0.52
    ầng
    0.50
     alignments
    0.48
    𝘳
    0.48
    AppBsky
    0.47
     तुम्ह
    0.47
    ğe
    0.47
    ੰਜ
    0.47
    Activations Density 0.010%

    No Known Activations