© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13347
    Prev
    Next
    INDEX
    Explanations

    dumpsters, trouble, choosing, locations, recession

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

    conditional statements starting with "if"

    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_16k_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
     πρώτη
    0.48
    ΠΟ
    0.48
     Podium
    0.47
     risiko
    0.46
     pediat
    0.46
    𝑁
    0.46
     Register
    0.46
    Footer
    0.45
     Peb
    0.45
    腴
    0.45
    POSITIVE LOGITS
     outlaw
    0.47
    witness
    0.46
     happenings
    0.45
    ősz
    0.42
     nightclubs
    0.42
     undercover
    0.42
    inse
    0.42
     outcast
    0.42
    };\
    0.42
     interconnected
    0.42
    Activations Density 0.006%

    No Known Activations