© 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. 137692
    Prev
    Next
    INDEX
    Explanations

    holder of

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

    current status and analysis

    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
    ilberger
    0.49
     جوړونکی
    0.48
     مسئلہ
    0.48
    myCollision
    0.46
    zarchiwizowane
    0.45
    筆
    0.45
    學院
    0.45
    politics
    0.44
    bandSize
    0.44
    漃
    0.44
    POSITIVE LOGITS
     cation
    0.51
     chromatin
    0.50
     a
    0.48
     infiltr
    0.46
     anglers
    0.45
     ran
    0.45
     UBS
    0.45
     ruh
    0.45
     Kurdistan
    0.45
     kits
    0.44
    Activations Density 0.000%

    No Known Activations