© 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. 40115
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
     zespół
    0.52
    ギリス
    0.49
    ักษณะ
    0.47
     obecnie
    0.46
    0.45
    </h3>
    0.45
    ון
    0.44
    人材
    0.44
     aika
    0.44
     cromosoma
    0.44
    POSITIVE LOGITS
    ت
    0.85
    ed
    0.80
    q
    0.66
     went
    0.62
    took
    0.62
     took
    0.62
     volna
    0.62
    了他的
    0.62
    pl
    0.60
    ла
    0.60
    Activations Density 0.066%

    No Known Activations