© 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. 16576
    Prev
    Next
    INDEX
    Explanations

    bungee jump, solar plexus

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

    foreign language etc

    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
    :
    0.66
    8
    0.45
    URI
    0.45
     pathophys
    0.44
    KE
    0.43
    RE
    0.42
    ITH
    0.42
    कामा
    0.42
    .
    0.41
    UE
    0.41
    POSITIVE LOGITS
     Almanya
    0.48
     тощо
    0.46
     সবই
    0.45
     इत्यादी
    0.43
     vjer
    0.40
     stanie
    0.40
     naciones
    0.40
     Mudah
    0.39
     hiệu
    0.38
     danno
    0.38
    Activations Density 0.116%

    No Known Activations