© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2152
    Prev
    Next
    INDEX
    Explanations

    scalability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    壘
    0.39
    ხვევ
    0.37
    ணை
    0.37
    ೆಯನ್ನು
    0.37
     ساين
    0.37
    swick
    0.36
    نامج
    0.36
    lbrace
    0.36
    镭
    0.36
    过多
    0.36
    POSITIVE LOGITS
    Scal
    1.36
     Scal
    1.26
     scalability
    1.21
     scal
    1.17
    scal
    1.12
     scaling
    1.07
    Scaling
    1.05
     scalable
    1.04
     масшта
    1.00
     Scaling
    1.00
    Activations Density 0.016%

    No Known Activations