© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125880
    Prev
    Next
    INDEX
    Explanations

    phrase followed by punctuation or a new concept

    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
     Decomposition
    0.54
     Induction
    0.45
     an
    0.44
    寘
    0.43
     flops
    0.43
     is
    0.43
    Hai
    0.43
    ，
    0.42
     Ammonia
    0.42
     states
    0.41
    POSITIVE LOGITS
     రె
    0.49
    epte
    0.45
     ಜನರು
    0.44
     کرد
    0.43
     አማ
    0.42
     durata
    0.42
    studentid
    0.42
    ędzy
    0.40
    HERE
    0.39
    день
    0.39
    Activations Density 0.001%

    No Known Activations