© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1690
    Prev
    Next
    INDEX
    Explanations

    describing attributes or states

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

    "been afraid"

    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_53_width_65k_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
     ⿱
    0.19
    पुर
    0.19
    <0x0D>
    0.18
    <0xE2>
    0.18
     Huffman
    0.17
    сила
    0.17
    とい
    0.17
    আজ
    0.17
    ビ
    0.17
    }}=\
    0.16
    POSITIVE LOGITS
    <unused2110>
    0.20
    രുത്
    0.19
     tcpHeader
    0.18
    owego
    0.18
    <unused2121>
    0.18
    tDBOutput
    0.17
     popOperand
    0.17
     کمپنیوں
    0.17
     تكونوا
    0.17
    <unused2133>
    0.17
    Activations Density 0.271%

    No Known Activations