© 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. 204258
    Prev
    Next
    INDEX
    Explanations

    words/phrases at end of common phrases

    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
     Verenigde
    0.61
     twierd
    0.53
    ឌ
    0.53
     internationales
    0.52
     autochtones
    0.50
     fáciles
    0.50
    𝗈
    0.49
     atrocities
    0.49
    皚
    0.48
     vrijdag
    0.48
    POSITIVE LOGITS
    .
    0.44
     gloss
    0.42
    for
    0.40
    ment
    0.40
    Default
    0.40
    ष्ठ
    0.38
     for
    0.38
     contents
    0.36
     Ignore
    0.36
    List
    0.36
    Activations Density 0.004%

    No Known Activations