© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79252
    Prev
    Next
    INDEX
    Explanations

    spare parts

    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
    orong
    -0.80
     которыми
    -0.75
    bumptech
    -0.71
    ❋
    -0.71
    ]='
    -0.71
    мель
    -0.69
     contexto
    -0.69
     trabalhando
    -0.69
     dabar
    -0.69
    =]
    -0.69
    POSITIVE LOGITS
     parts
    6.06
    parts
    4.63
     Parts
    4.44
    Parts
    4.38
     PARTS
    3.81
    PARTS
    3.47
     części
    3.33
     partes
    3.20
    パーツ
    3.06
     spare
    3.02
    Activations Density 0.067%

    No Known Activations