© 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. 64728
    Prev
    Next
    INDEX
    Explanations

    song single bonus track

    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
     desafíos
    -0.81
     farmacia
    -0.75
    فره
    -0.74
    sigh
    -0.72
     Reprinted
    -0.71
    obt
    -0.71
     ácidos
    -0.69
    ሴ
    -0.69
    ('%
    -0.68
    𝑷
    -0.68
    POSITIVE LOGITS
     B
    2.56
     b
    2.03
    B
    1.75
     flip
    1.41
    Side
    1.41
     Side
    1.39
     side
    1.38
    カップ
    1.38
     ب
    1.32
    side
    1.31
    Activations Density 0.097%

    No Known Activations