© 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. 68337
    Prev
    Next
    INDEX
    Explanations

    Naeng Myeon

    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
    ⃙
    -2.25
     precau
    -2.22
    ativement
    -2.19
    ጵ
    -2.14
    洇
    -2.08
     posib
    -2.02
     higien
    -2.00
    čnega
    -2.00
    趿
    -1.99
     conversa
    -1.98
    POSITIVE LOGITS
    3
    2.73
    4
    2.64
    2
    2.44
    7
    2.17
    6
    2.17
    w
    2.16
    8
    2.06
    5
    2.06
    it
    1.98
    ar
    1.98
    Activations Density 0.001%

    No Known Activations