© 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. 160226
    Prev
    Next
    INDEX
    Explanations

    make, designed

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

    Zoomers, disruptive, shell, jailbreaking, automation, long tail, retrocommissioning, buffer

    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
     patriot
    0.53
     heartbreak
    0.52
     patriotism
    0.52
     representante
    0.52
     patriots
    0.52
     heartbroken
    0.50
     Ж
    0.49
     Ј
    0.49
     ရက်
    0.48
     java
    0.48
    POSITIVE LOGITS
    PL
    0.57
    FO
    0.55
    Moore
    0.49
    PE
    0.48
    चे
    0.48
    BOARD
    0.48
    PLA
    0.48
    Functional
    0.47
    AD
    0.46
    Zhang
    0.46
    Activations Density 0.000%

    No Known Activations