© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5246
    Prev
    Next
    INDEX
    Explanations

    sentiment analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     recreating
    1.69
    追い
    1.58
     masak
    1.55
     recreate
    1.54
    laquo
    1.53
    แยก
    1.52
    ampil
    1.50
    縷
    1.48
    궜
    1.47
    ]!=
    1.47
    POSITIVE LOGITS
    untz
    0.93
    orable
    0.90
    reon
    0.87
     VLAN
    0.84
    씩
    0.81
     adverb
    0.79
     INTE
    0.79
    이크
    0.78
    alea
    0.77
     noun
    0.76
    Activations Density 0.050%

    No Known Activations