© 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. 118316
    Prev
    Next
    INDEX
    Explanations

    ionic salts and counterions

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical compounds and ions in scientific literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     sulfide
    -0.88
    рабо
    -0.84
    breadcrumbs
    -0.83
     hedge
    -0.75
     sulphide
    -0.74
    浒
    -0.74
     trận
    -0.73
    リース
    -0.72
    jointe
    -0.72
     ут
    -0.72
    POSITIVE LOGITS
    PF
    1.07
    BF
    1.00
     BF
    0.97
    Tf
    0.91
     PF
    0.91
     Tf
    0.91
     counter
    0.88
    Counter
    0.83
     TF
    0.79
    TF
    0.74
    Activations Density 0.080%

    No Known Activations