© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109692
    Prev
    Next
    INDEX
    Explanations

    rank

    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
     leal
    -0.88
    ündete
    -0.87
     Puritans
    -0.86
     douche
    -0.85
    fortunately
    -0.85
    端的
    -0.84
     folgendes
    -0.83
    로그
    -0.82
    Pesquisa
    -0.82
    iented
    -0.82
    POSITIVE LOGITS
    rank
    1.87
     Rank
    1.79
     rank
    1.68
     RANK
    1.40
    Rank
    1.37
    able
    1.20
     ranks
    1.19
    er
    1.17
    RANK
    1.15
     ranking
    1.12
    Activations Density 0.011%

    No Known Activations