© 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. 48329
    Prev
    Next
    INDEX
    Explanations

    blood space, mechanical wave

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

    exploring opportunities

    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
    Dim
    0.55
    -
    0.50
     dim
    0.47
    Social
    0.46
     Dim
    0.46
    Sure
    0.46
     promises
    0.46
     social
    0.46
    人
    0.44
    ly
    0.44
    POSITIVE LOGITS
     aktivieren
    0.50
     natomiast
    0.48
    ljenje
    0.47
    addena
    0.47
     exerce
    0.47
     pierws
    0.47
     фрук
    0.47
     ಖರೀ
    0.46
     ejercer
    0.46
     Pierws
    0.46
    Activations Density 0.000%

    No Known Activations