© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42508
    Prev
    Next
    INDEX
    Explanations

    permission is granted

    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
    </b>
    -1.38
     ему
    -1.28
     femei
    -1.17
     Antar
    -1.12
    のおかげ
    -1.11
     sklo
    -1.07
     PÅ
    -1.06
     najbol
    -1.04
     vollständige
    -1.02
    łoż
    -1.01
    POSITIVE LOGITS
    赑
    1.33
    pography
    1.27
    cept
    1.27
    omorphisms
    1.21
     once
    1.21
    Diva
    1.20
     ПА
    1.15
     instead
    1.15
    乄
    1.15
    IContainer
    1.14
    Activations Density 0.939%

    No Known Activations