© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 841
    Prev
    Next
    INDEX
    Explanations

    contrasting clauses

    np_acts-logits-general · gemini-2.5-flash-lite

    but followed by qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    มัน
    0.24
     এই
    0.23
     عندنا
    0.23
    當
    0.23
    ?
    0.22
     ใน
    0.22
    要是
    0.22
    0.22
    この
    0.22
     عمر
    0.22
    POSITIVE LOGITS
     kept
    0.25
     switched
    0.24
    estay
    0.23
     prohibits
    0.23
     adds
    0.22
    ens
    0.21
    ospels
    0.21
     unable
    0.21
     stayed
    0.21
    ulate
    0.21
    Activations Density 0.098%

    No Known Activations