© 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. 5730
    Prev
    Next
    INDEX
    Explanations

    names and places after prepositions

    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
    ’
    0.26
    </h2>
    0.25
     eser
    0.22
     Multivariate
    0.22
    พวก
    0.22
    什么是
    0.22
    ʻ
    0.22
    /**
    0.22
     พวก
    0.21
     Origami
    0.21
    POSITIVE LOGITS
     colitis
    0.23
    াবু
    0.22
    цију
    0.21
    <unused303>
    0.21
    밂
    0.21
    베이스
    0.21
     என்பவர்
    0.21
    ヒ
    0.21
    ートル
    0.20
    ције
    0.20
    Activations Density 0.060%

    No Known Activations