© 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. 129975
    Prev
    Next
    INDEX
    Explanations

    location, category, or thing

    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
    }}_
    -1.09
    смотрим
    -1.08
     antwoord
    -1.02
    coledì
    -0.93
    opoly
    -0.89
    |}\
    -0.88
     esqueleto
    -0.88
    ٹر
    -0.87
    >")
    -0.87
    __.__
    -0.86
    POSITIVE LOGITS
     that
    1.04
    ὰ
    0.98
     which
    0.89
    imed
    0.86
    Z
    0.84
    參考文獻
    0.83
     D
    0.83
     J
    0.81
     kuid
    0.80
     T
    0.79
    Activations Density 0.055%

    No Known Activations