© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212716
    Prev
    Next
    INDEX
    Explanations

    structure and differentiation

    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_40_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
    denoted
    0.45
     denoted
    0.42
     denoting
    0.41
    ▛
    0.40
    entuan
    0.40
    لوث
    0.37
    ደበ
    0.37
    透
    0.37
     Bloc
    0.37
    突き
    0.37
    POSITIVE LOGITS
    Radius
    0.46
     бро
    0.42
     resistance
    0.41
     radius
    0.39
     கண்டு
    0.39
     backgroundColor
    0.38
     cubic
    0.38
    trial
    0.37
    Married
    0.37
     border
    0.37
    Activations Density 0.000%

    No Known Activations