© 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. 231814
    Prev
    Next
    INDEX
    Explanations

    items after "the"

    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
    urende
    0.50
    iin
    0.46
    最初
    0.45
    単位
    0.44
    يام
    0.44
    applicant
    0.44
    器
    0.44
    日本
    0.43
    iorno
    0.43
    有名
    0.43
    POSITIVE LOGITS
    Tracks
    0.52
     Prend
    0.50
    क्योंकि
    0.48
    ሱስ
    0.46
    Inject
    0.46
    ά
    0.46
     Found
    0.45
    Sandbox
    0.44
    Eh
    0.44
     kic
    0.43
    Activations Density 0.002%

    No Known Activations