© 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-16K
    7. 4790
    Prev
    Next
    INDEX
    Explanations

    within or and

    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_16k_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
     A
    0.57
     The
    0.48
     opted
    0.47
    A
    0.46
     have
    0.44
    de
    0.42
     values
    0.42
    iya
    0.42
    oos
    0.42
     R
    0.42
    POSITIVE LOGITS
     WITHIN
    0.55
    within
    0.50
    時に
    0.48
     WITHOUT
    0.48
    んに
    0.48
     within
    0.48
     towar
    0.48
     중에서
    0.47
    стрее
    0.46
     toj
    0.45
    Activations Density 0.263%

    No Known Activations