© 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. 22-GEMMASCOPE-RES-131K
    7. 65439
    Prev
    Next
    INDEX
    Explanations

    KETOFEN, Saltillo, Having fun

    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_22/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
     Instagram
    -1.39
     подозре
    -1.28
     étrangère
    -1.26
     кури
    -1.20
    ּוֹ
    -1.19
     system
    -1.14
    бочки
    -1.14
    ᾽
    -1.13
     []:
    -1.13
     бампер
    -1.12
    POSITIVE LOGITS
     voedsel
    1.41
    Contexte
    1.34
     geschaffen
    1.17
     verwendeten
    1.16
    Etimología
    1.11
     фильтр
    1.11
    Lá
    1.11
     and
    1.10
     siguen
    1.09
     支援
    1.09
    Activations Density 0.001%

    No Known Activations