© 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. 98640
    Prev
    Next
    INDEX
    Explanations

    counter, hyper, bio, eco, hypo

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

    prefixes that relate to technology, science, or security concepts such as "hydro-", "hyper", "bio-", "cyber", and "counter-".

    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
    hlí
    -0.83
    vga
    -0.81
    ally
    -0.76
    rawData
    -0.76
    oration
    -0.75
     야
    -0.75
    ENTRE
    -0.75
     alcune
    -0.75
    charted
    -0.75
     alcuni
    -0.74
    POSITIVE LOGITS
    美女
    0.82
    척
    0.79
     illust
    0.78
     immobilier
    0.77
    Цены
    0.76
     Reli
    0.76
     Bounds
    0.76
    ֢
    0.75
     neurotic
    0.75
     valg
    0.75
    Activations Density 0.075%

    No Known Activations