© 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. 58950
    Prev
    Next
    INDEX
    Explanations

    subject says

    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
    Rozm
    -1.23
    commented
    -1.14
    Reported
    -1.11
    裥
    -1.09
     STATES
    -1.09
    ଶ
    -1.09
    ภาษา
    -1.09
    Warn
    -1.05
    AFFIRMED
    -1.05
    jte
    -1.04
    POSITIVE LOGITS
     said
    7.09
     says
    3.52
     say
    3.45
     saying
    2.59
    said
    2.58
    说
    2.56
    說
    2.48
     mengatakan
    2.42
     gesagt
    2.20
     сказать
    2.16
    Activations Density 0.074%

    No Known Activations