© 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. 9273
    Prev
    Next
    INDEX
    Explanations

    time around iteration

    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
    medriver
    -1.88
    選べる
    -1.75
    鴴
    -1.73
     現貨
    -1.67
     Púb
    -1.64
    OUTUBE
    -1.63
    俨
    -1.52
    那时候
    -1.48
     Públicas
    -1.48
     Beide
    -1.47
    POSITIVE LOGITS
    i
    2.36
    r
    2.11
    The
    2.09
    l
    2.00
    ſelves
    1.92
    k
    1.84
    u
    1.80
    x
    1.79
    v
    1.73
    ll
    1.70
    Activations Density 0.005%

    No Known Activations