© 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. 5951
    Prev
    Next
    INDEX
    Explanations

    version, text, `if`

    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
    :
    0.75
    ın
    0.52
    **:
    0.50
     for
    0.48
    ):
    0.48
     For
    0.48
    .:
    0.48
     waar
    0.47
    :**
    0.46
    ”:
    0.46
    POSITIVE LOGITS
    目的是
    0.52
     είναι
    0.52
    物は
    0.52
    方法は
    0.50
    色は
    0.49
    意思是
    0.48
     প্রকল্পটি
    0.48
    時間は
    0.48
     দলটি
    0.47
     यह
    0.47
    Activations Density 0.182%

    No Known Activations