© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11533
    Prev
    Next
    INDEX
    Explanations

    cannot give

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     and
    1.52
     &
    1.22
     O
    1.17
     AND
    1.16
    IN
    1.07
     Z
    1.04
     IN
    1.04
    e
    1.04
     I
    1.03
     Doesn
    1.03
    POSITIVE LOGITS
     други
    1.25
    ти
    1.15
    陼
    1.12
    其它
    1.10
    笫
    1.09
    一個
    1.07
    ålet
    1.06
     наличие
    1.05
    ulter
    1.05
    癹
    1.03
    Activations Density 2.109%

    No Known Activations