© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3722
    Prev
    Next
    INDEX
    Explanations

    past tense, perfect tense, participle

    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_all/layer_41_width_262k_l0_big
    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
    herlands
    0.44
    ืน
    0.44
    physiological
    0.44
    সমান
    0.42
     POSITION
    0.42
     numerically
    0.42
    ックレス
    0.41
    鈣
    0.41
    adjacency
    0.41
    ৃদ্ধ
    0.41
    POSITIVE LOGITS
     tense
    1.18
    tense
    0.80
     Past
    0.72
     past
    0.66
     Perfect
    0.66
    Past
    0.64
     परफेक्ट
    0.64
     perfect
    0.63
    past
    0.60
    Perfect
    0.58
    Activations Density 0.012%

    No Known Activations