© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30284
    Prev
    Next
    INDEX
    Explanations

    lends itself to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auttaa
    -0.89
     berkualitas
    -0.86
    luke
    -0.85
    футбо
    -0.84
    辞
    -0.82
     باغ
    -0.75
     ویت
    -0.74
     terdengar
    -0.73
     myös
    -0.72
     Gour
    -0.72
    POSITIVE LOGITS
     lend
    4.69
     lends
    4.53
     lending
    3.58
     lent
    3.50
    lend
    2.89
     Lend
    2.69
     Lending
    2.36
     amenable
    2.22
     loan
    2.13
     loaned
    2.03
    Activations Density 0.100%

    No Known Activations