© 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. 127606
    Prev
    Next
    INDEX
    Explanations

    break down or categorize

    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
    そして
    0.53
     and
    0.50
    และ
    0.49
     ਅਤੇ
    0.48
     и
    0.47
     এবং
    0.46
    并在
    0.46
     并
    0.45
    并
    0.45
    ുകയും
    0.43
    POSITIVE LOGITS
    cribable
    0.51
     worthy
    0.45
     cuyos
    0.45
     свой
    0.44
     tani
    0.44
    whose
    0.43
     amely
    0.43
     whose
    0.42
    pan
    0.42
     capace
    0.41
    Activations Density 0.120%

    No Known Activations