© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    George Street or Turkey

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

    policy, political, systemic changes

    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
    Ư
    0.44
    Ρ
    0.44
     multiplets
    0.42
     centric
    0.42
     데이터를
    0.42
     pastes
    0.40
     internals
    0.40
    $\--
    0.39
     canvases
    0.39
     genotypes
    0.38
    POSITIVE LOGITS
     нижней
    0.45
     Paryayvachi
    0.44
     служба
    0.43
     وزير
    0.43
     أمس
    0.43
    قبال
    0.42
    ؟
    0.42
     سهله
    0.42
    reya
    0.42
    adier
    0.41
    Activations Density 0.000%

    No Known Activations