© 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. 22-GEMMASCOPE-RES-131K
    7. 93325
    Prev
    Next
    INDEX
    Explanations

    Q: . 1. . guard youths

    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_22/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
     började
    -0.91
    游戏中
    -0.85
    
    -0.82
     coached
    -0.81
     lesquels
    -0.81
     såg
    -0.81
    といい
    -0.81
     podían
    -0.81
    Demografía
    -0.81
     kinda
    -0.81
    POSITIVE LOGITS
    نظر
    1.02
    }(),
    0.99
    થ
    0.99
    imientos
    0.98
    <eos>
    0.96
    animous
    0.94
    óta
    0.92
    一旁
    0.91
    zzie
    0.87
     đảm
    0.87
    Activations Density 0.000%

    No Known Activations