© 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. 138027
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific terms

    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
    বিজ্ঞ
    0.45
    मपुर
    0.43
    马
    0.43
    休
    0.42
     overestimated
    0.41
    cadherin
    0.40
     wearing
    0.40
    notch
    0.39
     Poo
    0.39
     અમને
    0.39
    POSITIVE LOGITS
    Themes
    0.54
    »;
    0.47
     (?)
    0.46
     \*
    0.45
     распоря
    0.45
     dispos
    0.44
     Themes
    0.44
    »,
    0.43
     beant
    0.43
     diverses
    0.41
    Activations Density 0.003%

    No Known Activations