© 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. 201184
    Prev
    Next
    INDEX
    Explanations

    legal and financial contexts

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

    complex topics and calculations

    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
    ércoles
    0.45
    enció
    0.44
    髹
    0.44
     ANGELES
    0.43
    ává
    0.43
     resent
    0.42
     VIAF
    0.42
     COMMUNITY
    0.41
    uenti
    0.41
     continú
    0.41
    POSITIVE LOGITS
    ۹
    0.49
     moot
    0.49
     hasty
    0.49
     haste
    0.48
     chemin
    0.47
     unterwegs
    0.47
     tingkat
    0.47
     highway
    0.46
    純正
    0.46
     lalu
    0.45
    Activations Density 0.001%

    No Known Activations