© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130384
    Prev
    Next
    INDEX
    Explanations

    type definitions

    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
    nin
    -0.97
    tifiable
    -0.96
    rigger
    -0.93
    Transk
    -0.91
    Kako
    -0.90
     owl
    -0.89
     سعيد
    -0.86
    isait
    -0.86
    Ꮜ
    -0.85
    mistic
    -0.84
    POSITIVE LOGITS
     type
    1.98
     types
    1.77
    Types
    1.45
     whether
    1.24
     типу
    1.23
     тип
    1.20
    の種類
    1.19
     different
    1.15
     Types
    1.15
    type
    1.13
    Activations Density 0.028%

    No Known Activations