© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53639
    Prev
    Next
    INDEX
    Explanations

    expanding on, prefer places, building trust

    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
    ר
    0.49
     consec
    0.48
     maintain
    0.47
    as
    0.45
     do
    0.45
     pozn
    0.43
     hug
    0.42
     part
    0.42
     prede
    0.41
     metaphor
    0.41
    POSITIVE LOGITS
    ᱠ
    0.51
     ordinairement
    0.48
    ່ຽ
    0.47
     пропа
    0.47
     бывают
    0.46
     WITH
    0.46
    South
    0.43
     কালে
    0.42
    West
    0.41
    -{\
    0.41
    Activations Density 0.005%

    No Known Activations