© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8333
    Prev
    Next
    INDEX
    Explanations

    prepositions linking entities

    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
    ástico
    0.36
     ძალი
    0.33
    owanej
    0.32
    শ্
    0.32
    -->'
    0.32
    ড়ান্ত
    0.32
     চীৎকার
    0.31
    jLabel
    0.31
     photoshoot
    0.31
     ऑग
    0.31
    POSITIVE LOGITS
     adultos
    0.33
     persones
    0.33
     individuals
    0.31
    ↵↵
    0.30
     humans
    0.29
     awọn
    0.29
     adults
    0.29
     both
    0.29
     افراد
    0.29
     terceros
    0.28
    Activations Density 0.361%

    No Known Activations