© 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-65K
    7. 63246
    Prev
    Next
    INDEX
    Explanations

    mostly about nouns and their related contexts

    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_65k_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
     tumours
    0.47
     дает
    0.44
    嗟
    0.42
    unternehmen
    0.41
    企業
    0.40
    isers
    0.40
     විට
    0.40
     ಉತ್ಪ
    0.40
    }"
    0.40
     ලැබ
    0.40
    POSITIVE LOGITS
     principalmente
    0.48
     mostly
    0.43
     głównie
    0.41
     بعض
    0.40
     başta
    0.40
     mainly
    0.39
     underestimated
    0.39
     most
    0.38
     ceci
    0.38
     কমপক্ষে
    0.38
    Activations Density 0.008%

    No Known Activations