© 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. 34-GEMMASCOPE-RES-131K
    7. 80749
    Prev
    Next
    INDEX
    Explanations

    sameness and repetition

    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
    idable
    -0.92
    嫔
    -0.87
    fuls
    -0.84
     Incompatible
    -0.84
     asynchronously
    -0.84
    Джере
    -0.83
    ambiguation
    -0.83
     Erzb
    -0.82
    AllowAnonymous
    -0.81
    antium
    -0.81
    POSITIVE LOGITS
     repetitive
    2.64
     repetition
    2.44
     repeating
    2.41
     repeats
    2.33
    重复
    2.33
     repetir
    2.16
     repeated
    2.13
     same
    2.11
     repeti
    2.09
    repeated
    2.03
    Activations Density 0.087%

    No Known Activations