© 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. 34-GEMMASCOPE-RES-131K
    7. 76764
    Prev
    Next
    INDEX
    Explanations

    technical acronyms

    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_34/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
     (
    -1.33
     our
    -1.11
    一旁的
    -1.05
    （
    -1.05
    –
    -1.05
    $-$
    -1.02
    </td>
    -1.01
    ')).
    -1.00
    他想
    -0.98
    ।
    -0.96
    POSITIVE LOGITS
     siyang
    1.25
     görd
    1.20
    Üdv
    1.20
    🖇
    1.16
    Szia
    1.16
    when
    1.13
    Penulis
    1.10
    Один
    1.09
    Поздрав
    1.09
    pueden
    1.07
    Activations Density 0.257%

    No Known Activations