© 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. 7-GEMMASCOPE-2-RES-16K
    7. 138
    Prev
    Next
    INDEX
    Explanations

    of [possessive/noun]

    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
     is
    1.31
     in
    1.28
    .
    1.27
    ,
    1.22
     has
    1.20
     have
    1.20
    ’
    1.19
     to
    1.16
     for
    1.11
     of
    1.11
    POSITIVE LOGITS
    localVarHTTP
    1.28
    𒅈
    1.22
    kepsilon
    1.21
    ഷ്ട്ര
    1.20
    𒌇
    1.20
    𒆕
    1.19
    rfImp
    1.19
    nashvillehousing
    1.18
    scpService
    1.18
    SRPCS
    1.18
    Activations Density 1.609%

    No Known Activations