© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23508
    Prev
    Next
    INDEX
    Explanations

    unofficial, informal, unwritten

    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_34/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
    INTRO
    -0.78
     estrema
    -0.74
    rra
    -0.74
    瀉
    -0.73
    numb
    -0.73
    ovr
    -0.71
    æg
    -0.71
    overrightarrow
    -0.70
    fez
    -0.70
     exac
    -0.69
    POSITIVE LOGITS
     informal
    5.19
     unofficial
    5.00
     Informal
    4.13
     informally
    4.09
    Informal
    3.97
    inform
    2.75
     нео
    2.31
     unwritten
    2.19
     casual
    2.02
     INFORM
    1.88
    Activations Density 0.170%

    No Known Activations