© 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. 37512
    Prev
    Next
    INDEX
    Explanations

    certain words and what follows

    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
    mersive
    0.42
    破
    0.42
    After
    0.41
    Fighting
    0.40
     للنساء
    0.40
    ​
    0.40
     روند
    0.39
    潜
    0.39
    Duration
    0.39
     ਕਰ
    0.39
    POSITIVE LOGITS
     Governorate
    0.51
     Continuando
    0.46
     করিয়াছেন
    0.45
     Adapun
    0.45
    руем
    0.45
     бывают
    0.44
     あれ
    0.44
     Englishmen
    0.44
     Dioxide
    0.44
     चाहेंगे
    0.44
    Activations Density 0.001%

    No Known Activations