© 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-16K
    7. 1661
    Prev
    Next
    INDEX
    Explanations

    This is a phrase

    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
    ៖
    0.41
    :.
    0.40
    ༸
    0.39
    ா
    0.39
    йга
    0.38
    ackBar
    0.38
     funcional
    0.37
    ામ
    0.36
    ː
    0.35
    ɑ
    0.35
    POSITIVE LOGITS
     This
    0.46
     But
    0.43
     The
    0.42
     How
    0.42
     What
    0.40
     Southeast
    0.38
     Some
    0.38
     For
    0.38
     We
    0.37
     These
    0.37
    Activations Density 0.213%

    No Known Activations