© 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. 181777
    Prev
    Next
    INDEX
    Explanations

    PM resign

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

    innovation and resurgence

    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
     asemenea
    0.43
     hangar
    0.43
     handing
    0.43
    ጌ
    0.42
     segue
    0.42
     është
    0.41
     reluctantly
    0.41
     lẽ
    0.41
     hangs
    0.41
     संभालने
    0.41
    POSITIVE LOGITS
    Loksatta
    0.47
    MgSO
    0.47
    lN
    0.46
    pertino
    0.46
    Penny
    0.46
    ૄ
    0.44
    তিপ
    0.44
    orbidity
    0.43
    zné
    0.42
     Traction
    0.42
    Activations Density 0.000%

    No Known Activations