© 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-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5227
    Prev
    Next
    INDEX
    Explanations

    Ryzen RAM compatibility

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ,
    3.57
    (
    2.52
    .
    2.31
     (
    2.08
    '
    2.06
    :
    2.06
    ，
    2.01
    ’
    1.99
    ،
    1.80
    （
    1.80
    POSITIVE LOGITS
     actuation
    3.09
    tres
    2.98
     idling
    2.89
     ayatan
    2.85
    <end_of_image>
    2.82
     actuators
    2.80
     totalSupply
    2.77
    텍
    2.76
     makeSound
    2.75
    rinsic
    2.74
    Activations Density 0.487%

    No Known Activations