© 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. 13-GEMMASCOPE-2-RES-65K
    7. 396
    Prev
    Next
    INDEX
    Explanations

    that being

    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_13_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
    a
    3.44
    i
    3.22
    es
    2.96
    ه
    2.90
    া
    2.58
    й
    2.47
    에
    2.43
    ಿ
    2.39
    u
    2.30
    ed
    2.23
    POSITIVE LOGITS
    𝗺
    2.50
    ្នាំ
    2.46
    𝘁
    2.46
    schild
    2.37
    𝗼
    2.21
    亠
    2.18
    ाह
    2.17
    𝗲
    2.13
    𝗶
    2.08
    اا
    2.07
    Activations Density 0.907%

    No Known Activations