© 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. 26771
    Prev
    Next
    INDEX
    Explanations

    parent id, parent_id

    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
    bilirsiniz
    -0.93
     leven
    -0.90
    efel
    -0.85
    ceptives
    -0.84
    镂
    -0.83
     primeira
    -0.81
     grise
    -0.80
     Machu
    -0.80
    CRIPTION
    -0.80
    LETTER
    -0.80
    POSITIVE LOGITS
     décid
    0.86
     cometer
    0.85
     dévou
    0.84
    marco
    0.83
    assertNull
    0.82
    ৳
    0.81
     múl
    0.80
    irsten
    0.80
    برز
    0.80
    irte
    0.77
    Activations Density 0.004%

    No Known Activations