© 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. 10-GEMMASCOPE-RES-131K
    7. 970
    Prev
    Next
    INDEX
    Explanations

    guanine nucleotide, dtd, invariance

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

    names and technical terms like "INA", "DTD", "invariance", "guanine", and "inaudible".

    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_10/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
     takes
    -3.16
     strives
    -3.11
     longstanding
    -2.92
     sizable
    -2.91
     plethora
    -2.89
     facilitates
    -2.88
     sizeable
    -2.84
     undeniably
    -2.84
     phenomenal
    -2.83
     multifaceted
    -2.83
    POSITIVE LOGITS
     shimmering
    3.06
    1
    3.05
     dando
    3.02
     delightfully
    2.94
     remarkably
    2.94
     flashy
    2.89
    9
    2.89
     ridiculously
    2.89
     ludicrous
    2.81
     overly
    2.78
    Activations Density 0.004%

    No Known Activations