© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6998
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What is the"

    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_12_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
    まさ
    2.32
     therein
    2.28
     therewith
    2.28
    竟
    2.27
     marvell
    2.26
     acolo
    2.22
     ấy
    2.21
    咁
    2.15
     marvellous
    2.13
     Ahí
    2.12
    POSITIVE LOGITS
     primary
    1.42
     major
    1.34
    _(
    1.29
     C
    1.18
     U
    1.17
     during
    1.16
     W
    1.10
     MOST
    1.09
     parent
    1.09
    𝐶
    1.09
    Activations Density 0.049%

    No Known Activations