© 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. 95463
    Prev
    Next
    INDEX
    Explanations

    starting words of sentences

    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
     and
    -1.44
     or
    -1.23
    Ingredi
    -1.05
    寳
    -1.05
    ỡng
    -1.03
    bouncycastle
    -1.02
     ALWAYS
    -1.02
     medlemmer
    -1.02
    pullover
    -1.00
     other
    -0.98
    POSITIVE LOGITS
    Firstly
    1.74
     firstly
    1.69
     Firstly
    1.52
     I
    1.36
     einerseits
    1.26
    首先
    1.22
     сначала
    1.20
     primero
    1.20
     haupts
    1.20
    まず
    1.19
    Activations Density 0.092%

    No Known Activations