© 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. 32697
    Prev
    Next
    INDEX
    Explanations

    Kwon, predic, imitation, quarantine

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

    ETH

    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
    centerX
    0.44
    zeichnis
    0.42
    နောက်
    0.40
     کدام
    0.40
    }}\
    0.40
    ovskii
    0.40
    ulaire
    0.39
     কয়েকটি
    0.39
     CVD
    0.39
    }}+\
    0.37
    POSITIVE LOGITS
    Initially
    0.40
    로
    0.39
     vanaf
    0.39
    욱
    0.39
     quarant
    0.39
     imit
    0.39
    만
    0.38
    설
    0.38
     vanwege
    0.38
     otw
    0.38
    Activations Density 0.012%

    No Known Activations