© 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. 68305
    Prev
    Next
    INDEX
    Explanations

    scoreboards, composers, sheet

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

    grouping similar data points

    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
    reichen
    0.47
    oma
    0.46
    ergewöhn
    0.46
    ordan
    0.46
    وم
    0.45
    cade
    0.45
    觉
    0.45
    حد
    0.44
     podríamos
    0.44
    western
    0.44
    POSITIVE LOGITS
    ↵
    0.50
    </tr>
    0.46
     CSS
    0.46
     ./
    0.45
     changement
    0.45
     concurring
    0.42
    ahirkan
    0.41
    "./
    0.41
     PCI
    0.41
     renovating
    0.41
    Activations Density 0.004%

    No Known Activations