© 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. 10-GEMMASCOPE-RES-131K
    7. 101392
    Prev
    Next
    INDEX
    Explanations

    personal feelings and states

    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_10/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
     Ա
    -1.63
     always
    -1.56
    ⬮
    -1.53
    𖤣
    -1.48
     sostuvo
    -1.48
     bellissima
    -1.44
     landes
    -1.43
     sufficient
    -1.42
     advirtió
    -1.41
    ſelves
    -1.39
    POSITIVE LOGITS
    šní
    1.50
    尤其是
    1.49
     amelyek
    1.44
     takže
    1.42
    habitude
    1.40
     exacting
    1.37
    ülete
    1.34
     därför
    1.33
     terutama
    1.32
     vectorielle
    1.32
    Activations Density 0.075%

    No Known Activations