© 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. 69207
    Prev
    Next
    INDEX
    Explanations

    recommendations or utilities

    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
     including
    -1.38
     this
    -1.38
    tigheter
    -1.23
     incluir
    -1.20
     nasceu
    -1.18
    hezza
    -1.18
    თ
    -1.18
     his
    -1.17
     urusan
    -1.17
     created
    -1.16
    POSITIVE LOGITS
    either
    1.55
    preferably
    1.43
     другие
    1.38
     deliciosos
    1.38
    あなたが
    1.35
    就可以了
    1.34
     mascarilla
    1.33
     if
    1.33
    食べられる
    1.31
     you
    1.30
    Activations Density 0.096%

    No Known Activations