© 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. 22-GEMMASCOPE-RES-131K
    4. 67324
    Prev
    Next
    INDEX
    Explanations

    Error handling and declarations

    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
     especially
    -1.26
     clear
    -1.05
     their
    -1.05
     like
    -1.05
     immediate
    -1.04
     with
    -1.03
     again
    -1.02
     often
    -1.02
     particularly
    -1.00
     certain
    -0.98
    POSITIVE LOGITS
     AppCompatTheme
    1.16
    꿰
    1.08
    deutung
    0.99
    wym
    0.98
     hiperten
    0.98
    utando
    0.98
     levier
    0.98
    Ꮥ
    0.98
    lungen
    0.97
    θος
    0.96
    Activations Density 0.011%

    No Known Activations