© 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. 122242
    Prev
    Next
    INDEX
    Explanations

    limited edition vinyl

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

    specific capabilities or structures

    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
     प्रतियोगी
    0.51
    慚
    0.50
    早い
    0.48
    څ
    0.48
     yrs
    0.47
    緋
    0.46
    صی
    0.46
    ိ
    0.46
     बयान
    0.46
    分かり
    0.46
    POSITIVE LOGITS
     Dyson
    0.50
     Pipes
    0.45
     блока
    0.45
     dys
    0.44
     pipes
    0.43
    illère
    0.43
     Moose
    0.41
    ется
    0.40
     Foundry
    0.40
     Pyramid
    0.40
    Activations Density 0.000%

    No Known Activations