© 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. 49690
    Prev
    Next
    INDEX
    Explanations

    days, Q, A, Le, Diver

    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
     bedeuten
    -0.91
     which
    -0.91
     firstly
    -0.84
    但她
    -0.83
    اعمال
    -0.81
     Händler
    -0.79
    /*"
    -0.77
    idity
    -0.77
    อื่น
    -0.76
     samego
    -0.76
    POSITIVE LOGITS
    НИЙ
    0.83
    UIControl
    0.81
     комплек
    0.80
     recueil
    0.79
    ными
    0.78
    因此
    0.77
    )}_{
    0.76
     твой
    0.75
    clang
    0.74
    коли
    0.74
    Activations Density 0.001%

    No Known Activations