© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 151955
    Prev
    Next
    INDEX
    Explanations

    Dr. compromised account

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

    depending on

    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
    节日
    0.49
     newbies
    0.48
     വനി
    0.48
    诚
    0.45
    办公室
    0.45
    和社会
    0.45
     contented
    0.44
    AlertType
    0.43
    寥
    0.43
    趸
    0.43
    POSITIVE LOGITS
     range
    0.49
     not
    0.47
    access
    0.46
    evidence
    0.46
     accuse
    0.46
     depending
    0.45
     sensor
    0.45
    remote
    0.45
     dilation
    0.45
     secretions
    0.45
    Activations Density 0.001%

    No Known Activations