© 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. 50133
    Prev
    Next
    INDEX
    Explanations

    code initialization and declarations

    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
     housed
    -0.84
     Textil
    -0.77
     ся
    -0.74
    alek
    -0.73
     髪
    -0.71
    hydrox
    -0.71
     prayed
    -0.69
     ст
    -0.68
     wielded
    -0.68
    Cliff
    -0.67
    POSITIVE LOGITS
     setIs
    0.97
    ίζ
    0.94
    }=\{
    0.79
    udad
    0.79
     nachdem
    0.77
    elapsed
    0.75
    tadora
    0.75
     diode
    0.74
    ñata
    0.73
    lamations
    0.73
    Activations Density 0.021%

    No Known Activations