© 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. 59025
    Prev
    Next
    INDEX
    Explanations

    salutations and greetings

    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
    ஂ
    -1.60
     wybrać
    -1.56
    …..
    -1.52
    .....
    -1.49
    ]
    -1.48
    ine
    -1.46
    “
    -1.45
     a
    -1.44
    ....
    -1.43
    best
    -1.41
    POSITIVE LOGITS
     disminu
    1.65
    ्ञ
    1.57
     花纹
    1.55
    砗
    1.53
    僦
    1.52
    
    1.51
    躋
    1.50
    岽
    1.49
    淠
    1.48
    馀
    1.48
    Activations Density 0.028%

    No Known Activations