© 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. 99766
    Prev
    Next
    INDEX
    Explanations

    introducing additional details

    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
     empie
    0.60
     yemek
    0.51
    י
    0.51
     reconnaît
    0.49
     tip
    0.48
    桝
    0.48
     orifices
    0.47
    טח
    0.47
    hunger
    0.47
    ಿ
    0.46
    POSITIVE LOGITS
     Following
    0.53
     Specifically
    0.47
     Similar
    0.46
     Particularly
    0.46
    ानुसार
    0.46
    avlj
    0.46
     Several
    0.44
    p
    0.44
     Vitamin
    0.43
     culminating
    0.43
    Activations Density 0.002%

    No Known Activations