© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27027
    Prev
    Next
    INDEX
    Explanations

    can't change

    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
     simpel
    -1.21
     faktisk
    -1.21
     kuno
    -1.20
     authenti
    -1.16
     lakini
    -1.14
     alkoh
    -1.13
     kado
    -1.13
     kram
    -1.12
     pittores
    -1.12
     internes
    -1.11
    POSITIVE LOGITS
     during
    1.37
     later
    1.16
     when
    1.09
     data
    1.05
    覚えて
    1.05
     re
    1.02
     Sortiment
    0.97
     repeated
    0.96
     things
    0.94
     attributed
    0.94
    Activations Density 0.001%

    No Known Activations