© 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. 240493
    Prev
    Next
    INDEX
    Explanations

    arrived secretly, stopped from

    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
    ümer
    0.52
     cleansed
    0.51
     مسلح
    0.47
    ᱑
    0.45
    issão
    0.44
     మద్యం
    0.42
     място
    0.42
    wstring
    0.42
    üşt
    0.42
     sanitized
    0.42
    POSITIVE LOGITS
     altres
    0.47
    Goal
    0.45
     argue
    0.44
     Centrale
    0.44
    祐
    0.43
    സ്
    0.43
    dog
    0.43
     ignite
    0.43
     dietro
    0.43
     Allen
    0.42
    Activations Density 0.001%

    No Known Activations