© 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. 22-GEMMASCOPE-RES-131K
    7. 95584
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT statements

    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
     mej
    -0.93
     стомато
    -0.91
    Elev
    -0.91
     crouch
    -0.86
     cenu
    -0.86
    Lí
    -0.83
    Idem
    -0.82
     MÁ
    -0.82
     komunik
    -0.81
     komfort
    -0.81
    POSITIVE LOGITS
     pię
    0.85
     umě
    0.83
     poiché
    0.82
    itoba
    0.82
    ifornia
    0.81
    halation
    0.81
    TextEditing
    0.81
    boundaries
    0.81
     size
    0.80
     latach
    0.80
    Activations Density 0.022%

    No Known Activations