© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1567
    Prev
    Next
    INDEX
    Explanations

    conjunctions and translations

    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
     alike
    3.41
     tbh
    2.59
     lainnya
    2.48
     sebagainya
    2.40
     zugleich
    2.32
    dDays
    2.31
     "":
    2.25
     같습니다
    2.23
     비슷
    2.21
     др
    2.16
    POSITIVE LOGITS
     and
    9.06
     và
    7.16
    และ
    7.13
     и
    6.54
    and
    6.49
     dan
    6.35
    和
    6.10
     และ
    6.08
    および
    6.07
    そして
    6.04
    Activations Density 9.656%

    No Known Activations