© 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. 67760
    Prev
    Next
    INDEX
    Explanations

    local hospital, satellite phone

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

    internet mysteries, creepypastas, lost media

    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
    склю
    0.47
     ஆரோ
    0.47
    //
    0.46
     års
    0.44
     indicating
    0.43
     constructor
    0.43
     Roh
    0.43
    遄
    0.42
    发
    0.42
    。
    0.41
    POSITIVE LOGITS
     musul
    0.61
    aic
    0.52
     muslim
    0.48
    ನನ್ನು
    0.48
     ಎಷ್ಟು
    0.47
    emus
    0.46
    crafted
    0.45
     मुसलमान
    0.45
     vutto
    0.45
    muslim
    0.43
    Activations Density 0.001%

    No Known Activations