© 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. 161004
    Prev
    Next
    INDEX
    Explanations

    conditions and restrictions

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

    conflict and territorial outcomes

    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
    小学
    0.57
    两个
    0.57
    Ко
    0.55
    До
    0.55
    3
    0.54
    무
    0.52
    混合
    0.50
    Điều
    0.50
    Innovative
    0.50
    У
    0.47
    POSITIVE LOGITS
     remnants
    0.52
     relinqu
    0.51
     headquarters
    0.51
     rey
    0.50
     ceded
    0.50
     relinquished
    0.49
     keing
    0.48
     irgend
    0.47
     regain
    0.47
     revenge
    0.46
    Activations Density 0.011%

    No Known Activations