© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142390
    Prev
    Next
    INDEX
    Explanations

    support for Passenger or Power

    np_acts-logits-general · gemini-2.5-flash-lite

    combination of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setzen
    0.54
    嗗
    0.45
    ]
    0.44
    ↵
    0.43
    </h2>
    0.43
    Dru
    0.42
    ennem
    0.42
            
    0.42
    着
    0.42
     Elec
    0.41
    POSITIVE LOGITS
    ্ড
    0.51
     south
    0.50
     चीन
    0.50
     मार्ट
    0.49
     वी
    0.48
     maxY
    0.48
    strictly
    0.48
     morate
    0.47
     codified
    0.47
     violated
    0.47
    Activations Density 0.000%

    No Known Activations