© 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. 250962
    Prev
    Next
    INDEX
    Explanations

    and I

    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
    ាវ
    0.54
    曆
    0.50
    
    0.50
     Mitarbeiter
    0.50
    KeyboardView
    0.49
    matchCondition
    0.49
     pavil
    0.48
     Saison
    0.48
     Körper
    0.48
    skoj
    0.47
    POSITIVE LOGITS
    '')
    0.49
     topologies
    0.43
    st
    0.41
     ब्ल
    0.41
     sucked
    0.40
    ///
    0.40
     documents
    0.39
     formats
    0.39
    イナー
    0.39
     ignored
    0.39
    Activations Density 0.004%

    No Known Activations