© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8130
    Prev
    Next
    INDEX
    Explanations

    understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     बी
    0.35
     જોવા
    0.33
    })$.
    0.32
    氮
    0.32
     শোনা
    0.32
     नावा
    0.31
     బీ
    0.30
    肯
    0.30
    }^{\
    0.30
     Included
    0.30
    POSITIVE LOGITS
     recognises
    0.55
     understands
    0.54
     recognise
    0.52
     recognising
    0.50
     recognised
    0.50
     recognizes
    0.48
     understand
    0.48
     recognize
    0.47
     reconnaître
    0.47
     recognized
    0.47
    Activations Density 0.172%

    No Known Activations