© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1203
    Prev
    Next
    INDEX
    Explanations

    surname:

    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_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
    retch
    1.22
    istatic
    1.22
    newdata
    1.18
    tugraz
    1.12
    ventil
    1.11
     संपन्न
    1.11
    cing
    1.10
    尭
    1.09
    porcion
    1.09
     Mali
    1.09
    POSITIVE LOGITS
     moniker
    2.61
     name
    2.55
     nickname
    2.55
     이름
    2.45
     nicknames
    2.44
     names
    2.40
     이름을
    2.39
    名称
    2.35
    名字
    2.33
     suffix
    2.28
    Activations Density 1.518%

    No Known Activations