© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13292
    Prev
    Next
    INDEX
    Explanations

    protein synthesis and denaturation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    zustellen
    2.53
     ایست
    2.43
    মণ্ড
    2.42
     Awareness
    2.42
     m
    2.41
    ⓒ
    2.40
    irtschaft
    2.39
    తిక
    2.39
    peuta
    2.38
    häuse
    2.36
    POSITIVE LOGITS
    ーション
    3.04
    ھی
    2.73
    ရား
    2.57
    ềm
    2.56
    aneously
    2.56
    えます
    2.43
    ы
    2.42
    えて
    2.41
    rí
    2.39
    ಕ್ಷ
    2.38
    Activations Density 0.013%

    No Known Activations