© 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. 34-GEMMASCOPE-RES-131K
    7. 62954
    Prev
    Next
    INDEX
    Explanations

    Iceberg, Clinical Manifest, Skip Hire, Next steps, report, Tuesday, panel, protest

    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
     admittedly
    -1.06
     frankly
    -1.00
     our
    -0.98
     awesome
    -0.98
     vermittelt
    -0.96
    奬
    -0.91
    来店
    -0.90
     nagu
    -0.90
    ardians
    -0.90
     nicely
    -0.90
    POSITIVE LOGITS
    ּוֹ
    1.28
    
    1.06
    اااا
    1.04
     ⁠
    1.01
    Föld
    0.99
    ⟳
    0.98
    ñadir
    0.98
     वो
    0.98
    ਜ਼
    0.98
     ANI
    0.98
    Activations Density 0.035%

    No Known Activations