© 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-16K
    7. 2148
    Prev
    Next
    INDEX
    Explanations

    spring, spring boot, flirty, flourishing, courage, Celtic Tribal

    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
    Negative Logits
    єї
    1.60
    穌
    1.57
    א
    1.53
    uslar
    1.51
    ieves
    1.46
    一提
    1.45
    éges
    1.45
    listening
    1.45
    stood
    1.43
    Provided
    1.43
    POSITIVE LOGITS
    ierzchn
    1.59
    <0x0C>
    1.58
    elage
    1.54
    ство
    1.53
    ัพ
    1.53
    ishes
    1.52
    Kamp
    1.49
    ργαν
    1.46
     uko
    1.44
    slag
    1.43
    Activations Density 0.112%

    No Known Activations