© 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. 10-GEMMASCOPE-RES-131K
    7. 21577
    Prev
    Next
    INDEX
    Explanations

    fabled, famed, promised, illusive

    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
    鶫
    -1.61
    蘩
    -1.45
     carcasa
    -1.41
     perpé
    -1.40
    ᥫ
    -1.38
    ꩜
    -1.38
     óptica
    -1.38
    ⚢
    -1.37
    峮
    -1.37
     energii
    -1.36
    POSITIVE LOGITS
     Since
    1.73
     Then
    1.56
     new
    1.48
     more
    1.46
    s
    1.41
     Generally
    1.40
    ….
    1.37
     but
    1.33
     three
    1.32
     Interestingly
    1.30
    Activations Density 0.023%

    No Known Activations