© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109732
    Prev
    Next
    INDEX
    Explanations

    scoring and performance metrics

    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
     thưởng
    -0.78
    ANTE
    -0.77
    nsf
    -0.75
    éz
    -0.75
    роки
    -0.74
    それぞれ
    -0.74
     britannique
    -0.73
    رفه
    -0.73
    SUCCESS
    -0.71
     comenzó
    -0.71
    POSITIVE LOGITS
     scored
    3.86
     scoring
    3.72
     score
    3.03
    scoring
    2.89
     Scoring
    2.84
    scored
    2.77
    Scoring
    2.69
    score
    2.55
     scores
    2.34
    Score
    2.20
    Activations Density 0.063%

    No Known Activations