© 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. 69052
    Prev
    Next
    INDEX
    Explanations

    return to / back to

    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
    inerario
    -1.21
    siguiente
    -1.10
     a
    -1.05
     vedea
    -1.02
     different
    -0.98
     siguiente
    -0.97
     следующих
    -0.96
    vább
    -0.96
     Schrifts
    -0.94
    aned
    -0.93
    POSITIVE LOGITS
     our
    1.16
     снова
    1.09
     seçenek
    1.02
    に戻
    1.02
    chl
    1.02
    แล้ว
    0.97
     теперь
    0.95
     earlier
    0.95
     the
    0.95
    efi
    0.95
    Activations Density 0.005%

    No Known Activations