© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34501
    Prev
    Next
    INDEX
    Explanations

    MIDDLETOWN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Perhaps
    -1.26
    مقدمه
    -1.24
    Having
    -1.24
    Following
    -1.22
    Through
    -1.19
    Taking
    -1.13
    After
    -1.09
    Sometimes
    -1.07
    Despite
    -1.07
    Probably
    -1.06
    POSITIVE LOGITS
     sooo
    1.13
     ridiculously
    1.13
     unbelievably
    1.04
     soooo
    1.03
     amazingly
    1.02
     insanely
    1.02
     exhilarating
    1.00
    了不少
    0.99
     delectable
    0.97
     delightfully
    0.96
    Activations Density 0.002%

    No Known Activations