© 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. 37190
    Prev
    Next
    INDEX
    Explanations

    free software download access

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

    additional information and conditions

    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
     zunehm
    0.37
     compensation
    0.36
     pelayanan
    0.35
     خدا
    0.34
     तेजी
    0.34
    غذ
    0.34
    验证
    0.34
    </h3>
    0.34
     inexpensive
    0.34
    越来越多
    0.34
    POSITIVE LOGITS
     देखील
    0.45
    Alongside
    0.44
    微软雅黑
    0.43
     отлично
    0.43
     बाबर
    0.42
     сделали
    0.41
    Incidentally
    0.41
     রীতি
    0.41
     అర్జు
    0.41
    Attendee
    0.39
    Activations Density 0.012%

    No Known Activations