© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95436
    Prev
    Next
    INDEX
    Explanations

    joining clauses with and

    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
     biela
    -1.34
     baie
    -1.34
     multicolore
    -1.33
     zucca
    -1.31
     pê
    -1.31
     cortina
    -1.31
     maniere
    -1.28
     verdura
    -1.27
     notori
    -1.27
     hés
    -1.25
    POSITIVE LOGITS
    7
    1.48
    6
    1.30
    4
    1.24
    8
    1.22
    3
    1.20
     and
    1.20
    9
    1.17
    2
    1.13
    ,
    1.10
    5
    1.06
    Activations Density 0.018%

    No Known Activations