© 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. 236697
    Prev
    Next
    INDEX
    Explanations

    manual and automatic

    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
    sonaro
    0.48
     पीएम
    0.48
    kab
    0.48
    elah
    0.46
    uthi
    0.46
    🤏
    0.45
    straction
    0.45
     બનાવી
    0.45
    uts
    0.44
    ਮੀ
    0.44
    POSITIVE LOGITS
    رس
    0.52
     locations
    0.51
     verses
    0.50
     importation
    0.47
     emails
    0.46
    룸
    0.46
     versa
    0.46
     requirements
    0.44
     verse
    0.44
     referrals
    0.44
    Activations Density 0.000%

    No Known Activations