© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7041
    Prev
    Next
    INDEX
    Explanations

    object or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Valencia
    1.23
    Va
    1.18
     Solana
    1.15
     Va
    1.13
    Valencia
    1.11
     bets
    1.11
    Vil
    1.10
    炒
    1.09
    Doming
    1.09
     chocol
    1.09
    POSITIVE LOGITS
    евич
    1.22
    Objects
    1.21
    object
    1.16
     Objects
    1.12
    ubj
    1.12
     objek
    1.10
    对象的
    1.09
    AAF
    1.08
    Object
    1.07
    ObjectClass
    1.06
    Activations Density 0.022%

    No Known Activations