© 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. 71874
    Prev
    Next
    INDEX
    Explanations

    feeling "for" lease violations

    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
     regenv
    0.54
    ঠিত
    0.46
    ֒
    0.45
     dakkh
    0.45
    শনাল
    0.44
    adaki
    0.44
     temel
    0.43
     défi
    0.43
    ார
    0.43
    里的
    0.42
    POSITIVE LOGITS
    在
    0.52
     affiliates
    0.48
     সোসাই
    0.48
    ोन
    0.45
     intellectually
    0.44
     recruited
    0.42
     кре
    0.42
     ২০২২
    0.42
    も
    0.42
     यहीं
    0.42
    Activations Density 0.004%

    No Known Activations