© 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. 29477
    Prev
    Next
    INDEX
    Explanations

    levels of states or attributes

    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
     stopping
    0.43
     M
    0.42
    ång
    0.41
    ION
    0.40
     focuses
    0.38
     defeat
    0.38
     is
    0.37
    ian
    0.37
     problem
    0.36
     Register
    0.36
    POSITIVE LOGITS
     অনন্য
    0.42
    वियस
    0.40
    ぴったり
    0.39
    梶
    0.39
     inverse
    0.39
    inverse
    0.39
     उपेंद्र
    0.38
     Hinweise
    0.38
     특별
    0.38
     Casimir
    0.38
    Activations Density 0.000%

    No Known Activations