© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129159
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    𝙹
    -0.93
     Planeten
    -0.92
     način
    -0.89
    啶
    -0.86
     reasons
    -0.86
    entukan
    -0.84
    tvar
    -0.84
     konflik
    -0.83
     creativity
    -0.83
     Shaft
    -0.82
    POSITIVE LOGITS
    true
    1.01
    真正
    0.82
     perfect
    0.81
     true
    0.81
     ideal
    0.80
    ylabel
    0.72
    middels
    0.71
    Ideally
    0.69
    complish
    0.69
     ipo
    0.69
    Activations Density 0.043%

    No Known Activations