© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108659
    Prev
    Next
    INDEX
    Explanations

    especially or particularly

    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
     plafon
    -1.66
     вполне
    -1.45
    ícias
    -1.45
    𓆏
    -1.43
    albeit
    -1.41
     très
    -1.38
    uded
    -1.37
    骉
    -1.35
     disponibilités
    -1.35
    quite
    -1.35
    POSITIVE LOGITS
     important
    1.69
     suited
    1.64
     valuable
    1.53
     noteworthy
    1.53
     noticeable
    1.51
     useful
    1.48
     relevant
    1.44
     prevalent
    1.38
     notable
    1.37
     when
    1.36
    Activations Density 0.025%

    No Known Activations