© 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. 98835
    Prev
    Next
    INDEX
    Explanations

    horizon and distant views

    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
    Highlight
    -0.85
    >)</
    -0.83
     Avalanche
    -0.82
    ໊
    -0.82
     Parcelable
    -0.78
     puse
    -0.77
     reguli
    -0.76
     Highlight
    -0.76
    inode
    -0.76
    肤
    -0.75
    POSITIVE LOGITS
     horizon
    5.00
    horizon
    3.81
     horizons
    3.69
     Horizon
    3.25
    Horizon
    3.13
     horizonte
    2.94
     Horizons
    2.31
     гори
    2.19
    horiz
    1.98
     horiz
    1.84
    Activations Density 0.029%

    No Known Activations