© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30856
    Prev
    Next
    INDEX
    Explanations

    describing adjectives

    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
    了许多
    -1.11
     which
    -1.07
    ztes
    -1.05
    attribute
    -1.00
    ousness
    -0.99
    ceous
    -0.97
    了不少
    -0.93
    rangle
    -0.93
    了些
    -0.93
    ceae
    -0.92
    POSITIVE LOGITS
     likes
    2.08
     aforementioned
    1.63
     szint
    1.38
     equally
    1.37
     inim
    1.36
     toujours
    1.34
     ever
    1.29
     recently
    1.26
     mindig
    1.23
     afore
    1.23
    Activations Density 0.082%

    No Known Activations