© 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. 815
    Prev
    Next
    INDEX
    Explanations

    writing types of content

    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
     plummeted
    1.31
    igit
    1.31
     consigned
    1.29
    ppled
    1.28
    osate
    1.26
    Hepin
    1.24
    ciąż
    1.24
     Allí
    1.20
    ::<
    1.20
    łączy
    1.16
    POSITIVE LOGITS
     terbaik
    1.66
     useful
    1.55
     besten
    1.52
     καλύτε
    1.46
     examples
    1.46
     possible
    1.45
    according
    1.42
     mejores
    1.39
     explanation
    1.39
     meilleurs
    1.39
    Activations Density 1.446%

    No Known Activations