© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185465
    Prev
    Next
    INDEX
    Explanations

    cost and shipping

    np_acts-logits-general · gemini-2.5-flash-lite

    origin, obligations, country, niche

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ატი
    0.46
    >$
    0.46
    മായിരുന്നു
    0.43
     stér
    0.43
    διά
    0.41
     déterminer
    0.40
    ్రియ
    0.40
    verting
    0.40
    த்திலேயே
    0.40
    <0xAB>
    0.39
    POSITIVE LOGITS
     nef
    0.51
     berasal
    0.48
    skih
    0.46
    Nj
    0.45
     sevi
    0.45
    체를
    0.45
     җ
    0.44
     asper
    0.44
    c
    0.44
     ambitions
    0.44
    Activations Density 0.000%

    No Known Activations