© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1546
    Prev
    Next
    INDEX
    Explanations

    time to

    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
    </strong>
    -1.73
     pozdě
    -1.54
     όταν
    -1.51
     Constitucional
    -1.46
    vature
    -1.45
     esencial
    -1.42
    芨
    -1.39
    </h3>
    -1.38
     desblo
    -1.37
     conmemor
    -1.37
    POSITIVE LOGITS
    L
    1.53
    )
    1.44
     bourgeo
    1.43
     berger
    1.41
     coiff
    1.34
     پروفایل
    1.33
     tremb
    1.30
     authenti
    1.28
     pune
    1.28
     deniz
    1.27
    Activations Density 0.018%

    No Known Activations