© 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. 75315
    Prev
    Next
    INDEX
    Explanations

    minimizing squared differences

    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
     statesman
    0.42
    s
    0.41
     statesmen
    0.38
    Minister
    0.35
    remarkable
    0.35
     கவர்
    0.33
    prototype
    0.33
    特
    0.32
    ミ
    0.32
    膽
    0.32
    POSITIVE LOGITS
     использует
    0.46
     verwenden
    0.44
     Cube
    0.43
     предназначен
    0.41
     أوروبا
    0.41
     recomienda
    0.40
     permettent
    0.40
     umożliw
    0.39
     permite
    0.39
    觀塘
    0.38
    Activations Density 0.000%

    No Known Activations