© 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. 116645
    Prev
    Next
    INDEX
    Explanations

    investigational drug candidates

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

    names of pharmaceutical compounds and medical treatments in scientific or clinical contexts.

    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
     spirit
    -0.85
    BOB
    -0.84
     popular
    -0.75
     puissance
    -0.73
    Introdu
    -0.71
    楕
    -0.70
    じゃん
    -0.69
     multimedia
    -0.69
    Endor
    -0.69
    Dore
    -0.68
    POSITIVE LOGITS
     candidate
    1.31
     candidates
    1.27
     investig
    1.15
    candidate
    1.14
     orphan
    1.05
    asticity
    1.03
     Candidate
    1.02
     candidat
    1.02
     candidato
    1.02
     Candidates
    1.01
    Activations Density 0.160%

    No Known Activations