© 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. 93145
    Prev
    Next
    INDEX
    Explanations

    starts of specific phrases

    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
    sockfd
    -0.93
     stille
    -0.92
    стол
    -0.91
    angé
    -0.88
     anything
    -0.87
     parut
    -0.86
     profes
    -0.86
    OrEmpty
    -0.85
    !«
    -0.85
    ⟞
    -0.85
    POSITIVE LOGITS
    あげ
    0.89
    プール
    0.84
    ąc
    0.83
    左边
    0.81
     acquaint
    0.81
    ジャン
    0.81
     ему
    0.80
    虾
    0.79
     predetermin
    0.79
     cusp
    0.79
    Activations Density 0.000%

    No Known Activations