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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3260
    Prev
    Next
    INDEX
    Explanations

    connecting listed items

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

    input/output or conjunctions

    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
    ██
    0.38
    𝒆
    0.35
    𝘭
    0.35
    すぎて
    0.34
    об
    0.34
    ಕ್ಷಣ
    0.34
    .')
    0.34
    ')]
    0.34
    🇶
    0.33
    鈮
    0.33
    POSITIVE LOGITS
     especially
    0.46
    amp
    0.46
    lor
    0.45
    /
    0.43
     Also
    0.41
     its
    0.40
     also
    0.40
     همچنین
    0.40
     foremost
    0.39
     likewise
    0.39
    Activations Density 0.422%

    No Known Activations