© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 689
    Prev
    Next
    INDEX
    Explanations

    3D models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
    蜊
    1.44
    ordination
    1.41
     some
    1.40
    ulating
    1.40
     mycursor
    1.39
    ltry
    1.37
    явить
    1.24
     Some
    1.22
    iches
    1.21
    ogni
    1.21
    POSITIVE LOGITS
    0
    2.83
    8
    2.77
    5
    2.74
    4
    2.69
    6
    2.68
    7
    2.62
    9
    2.48
    º
    2.37
    つの
    2.32
    rd
    2.32
    Activations Density 1.127%

    No Known Activations