© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50304
    Prev
    Next
    INDEX
    Explanations

    toggle button

    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
     tsar
    -0.88
    w
    -0.88
     revolved
    -0.87
     marvel
    -0.84
     öfter
    -0.84
    żą
    -0.84
    Thats
    -0.83
    är
    -0.82
    ną
    -0.81
    EEK
    -0.80
    POSITIVE LOGITS
     between
    1.20
    Switch
    1.09
     switches
    1.05
    анна
    1.03
     switch
    1.02
    ВОД
    0.98
     compiled
    0.97
     switching
    0.97
     switched
    0.96
    豋
    0.96
    Activations Density 0.009%

    No Known Activations