© 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. 197640
    Prev
    Next
    INDEX
    Explanations

    the same goes for

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

    emphasis on literal understanding

    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
    sh
    0.48
    wi
    0.48
    potential
    0.47
    such
    0.46
    τη
    0.45
    ].
    0.44
    potato
    0.44
    western
    0.44
    off
    0.43
    </th>
    0.43
    POSITIVE LOGITS
     virtuelle
    0.52
     deinem
    0.50
     техні
    0.49
    േരി
    0.48
     ваше
    0.47
     ошиб
    0.46
     humild
    0.46
     техни
    0.45
    னுக்கு
    0.44
     பயிற்சி
    0.44
    Activations Density 0.001%

    No Known Activations