© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 134355
    Prev
    Next
    INDEX
    Explanations

    technical concepts and AI

    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
     hulls
    0.46
     ассорти
    0.45
     нати
    0.44
     volto
    0.42
     ৩
    0.42
     erfüllt
    0.42
     filles
    0.41
     Karlsson
    0.41
     космети
    0.41
    讪
    0.40
    POSITIVE LOGITS
    owner
    0.40
    োগ্য
    0.39
    ainless
    0.38
    severe
    0.38
    Together
    0.38
    years
    0.37
    thresh
    0.36
    Autumn
    0.35
    ail
    0.35
    license
    0.35
    Activations Density 0.000%

    No Known Activations