© 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. 243749
    Prev
    Next
    INDEX
    Explanations

    European Bank for Reconstruction and Development

    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
    en
    0.50
    tront
    0.49
     Policing
    0.49
    hevik
    0.48
    ᅦ
    0.45
     intervened
    0.45
    ಕರಣ
    0.45
    oscopes
    0.45
    ened
    0.44
     intrigued
    0.44
    POSITIVE LOGITS
     zam
    0.48
     água
    0.46
     física
    0.45
     zi
    0.44
     બી
    0.44
     PRES
    0.43
    '%
    0.43
     WoW
    0.43
     সেজন্য
    0.43
     mPreview
    0.43
    Activations Density 0.000%

    No Known Activations