© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64548
    Prev
    Next
    INDEX
    Explanations

    asking for help or advice

    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
     estuche
    -1.05
     centaines
    -1.04
     chercher
    -0.99
    沥
    -0.96
    νας
    -0.93
     embrague
    -0.93
     pratiquement
    -0.93
     aceasta
    -0.92
     milliers
    -0.91
     üst
    -0.90
    POSITIVE LOGITS
     tremendously
    1.63
     immensely
    1.57
     to
    1.54
     ích
    1.41
     when
    1.36
     enormously
    1.34
     in
    1.32
     greatly
    1.20
     for
    1.18
    ในการ
    1.18
    Activations Density 0.020%

    No Known Activations