© 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. 12066
    Prev
    Next
    INDEX
    Explanations

    security forces gain control

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

    code and natural language

    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
     kupu
    0.40
     बैठे
    0.39
    ములో
    0.38
    たく
    0.38
     قائم
    0.38
    elling
    0.38
    帏
    0.38
     турган
    0.37
    байд
    0.37
     groundwater
    0.37
    POSITIVE LOGITS
     accelerated
    0.44
     Accelerated
    0.42
    reporter
    0.39
     页
    0.38
     alienated
    0.37
    śl
    0.37
     REPORTER
    0.36
     OCT
    0.36
    ujj
    0.36
    uron
    0.35
    Activations Density 0.004%

    No Known Activations