© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49933
    Prev
    Next
    INDEX
    Explanations

    phrasal constructions ending in specific words

    np_acts-logits-general · gemini-2.5-flash-lite

    temporal features, camping, networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bits
    0.41
     partitions
    0.41
    noscript
    0.41
    ৱ
    0.41
    র
    0.40
     новом
    0.40
    Split
    0.40
    splits
    0.40
    ӗ
    0.40
    单
    0.40
    POSITIVE LOGITS
     अराउंड
    0.54
     वरिष्ठ
    0.53
     genieten
    0.53
     adhé
    0.52
    嗌
    0.50
     ਪਰ
    0.50
     alkohol
    0.49
     namik
    0.49
     amantes
    0.49
     épaisse
    0.49
    Activations Density 0.000%

    No Known Activations