© 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. 57241
    Prev
    Next
    INDEX
    Explanations

    litres per second

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

    exploration yields

    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
    ropy
    0.43
    </sub>
    0.43
    ness
    0.43
     άλλα
    0.43
    riches
    0.41
     Gle
    0.40
     Surfaces
    0.40
    णीय
    0.40
     congregations
    0.40
     incomparable
    0.40
    POSITIVE LOGITS
     potere
    0.45
     testigo
    0.43
     Cortana
    0.42
     ড্র
    0.42
    ത്തേക്ക്
    0.42
    شنبه
    0.42
    㤓
    0.41
    ush
    0.41
     sentir
    0.41
     प्रेशर
    0.41
    Activations Density 0.000%

    No Known Activations