© 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. 128677
    Prev
    Next
    INDEX
    Explanations

    free, release, liberation

    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
    怎么能
    -1.14
    谁能
    -1.02
     changes
    -1.02
    Trat
    -0.99
     stability
    -0.94
     θε
    -0.93
     возникает
    -0.93
     estabilidad
    -0.93
     shortcomings
    -0.91
     costuma
    -0.91
    POSITIVE LOGITS
     from
    1.33
     stuck
    1.17
    🤣🤣
    1.14
    😍😍
    1.13
     klasa
    1.07
    ]^{-
    1.05
    💀
    1.04
     freeing
    1.02
    😂😂
    1.02
    🤣🤣🤣
    1.00
    Activations Density 0.061%

    No Known Activations