© 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. 7736
    Prev
    Next
    INDEX
    Explanations

    also known, significantly higher

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

    market analysis and operations

    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
    Expires
    0.55
    expire
    0.51
    expires
    0.48
    কানিক্যাল
    0.48
     ৩৭
    0.48
    at
    0.46
    ᅣ
    0.45
     Moovit
    0.45
    jdk
    0.44
     책임
    0.44
    POSITIVE LOGITS
    س
    0.64
     hemisph
    0.52
     facil
    0.51
     صاح
    0.50
     submarine
    0.50
     uterus
    0.49
    вый
    0.49
     لن
    0.49
     लिह
    0.49
    िंग
    0.48
    Activations Density 0.000%

    No Known Activations