© 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. 33531
    Prev
    Next
    INDEX
    Explanations

    from above/below

    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
    ندما
    -0.81
    ijnlijk
    -0.81
     nuovamente
    -0.80
    arska
    -0.75
    حيان
    -0.75
     Crusoe
    -0.73
     dilat
    -0.72
     Dij
    -0.72
    ジナル
    -0.71
    Demografie
    -0.71
    POSITIVE LOGITS
     below
    3.11
     above
    2.98
     arriba
    2.45
     сверху
    2.27
     abajo
    2.25
     oben
    2.22
     upstairs
    2.17
    below
    2.13
    above
    2.11
     downstairs
    2.05
    Activations Density 0.047%

    No Known Activations