© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    This file describes

    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
     Advisory
    0.51
    us
    0.50
    üsü
    0.48
    ulagway
    0.47
    Nw
    0.46
     Requirement
    0.45
    芬
    0.45
    Φ
    0.45
     Química
    0.44
    Ｃ
    0.44
    POSITIVE LOGITS
     developmental
    0.56
     wobble
    0.52
     cosmic
    0.52
     dioc
    0.52
     projection
    0.51
     shimmering
    0.50
     dandelion
    0.50
     headway
    0.50
     lemon
    0.49
     decad
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.