© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    writing to express interest/concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    嘅
    2.27
    咁
    2.11
     التى
    2.03
     iaitu
    1.97
    攞
    1.92
     Whilst
    1.92
     realisation
    1.91
     Firstly
    1.91
    俾
    1.91
     sondern
    1.91
    POSITIVE LOGITS
    ].)
    1.36
     Landon
    1.35
    ꯠ
    1.29
     Calhoun
    1.28
    cón
    1.26
    aksi
    1.26
    antz
    1.25
     Sanford
    1.25
    chmal
    1.22
     Dorsey
    1.20
    Activations Density 0.140%

    No Known Activations