© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55592
    Prev
    Next
    INDEX
    Explanations

    Howard

    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
     collaborated
    -0.93
     большая
    -0.88
    こっち
    -0.84
    あなたは
    -0.82
     alongside
    -0.81
     constantly
    -0.81
    Conventional
    -0.81
     realistically
    -0.81
    خلا
    -0.80
     sophisticated
    -0.79
    POSITIVE LOGITS
     SHOULD
    0.91
     Taft
    0.90
    }^{+}
    0.90
    居る
    0.89
    are
    0.89
     Hughes
    0.89
     kuitenkin
    0.89
    shall
    0.88
    ʼ
    0.88
     тому
    0.87
    Activations Density 0.010%

    No Known Activations