© 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. 50145
    Prev
    Next
    INDEX
    Explanations

    squid, octopus, molluscs

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

    references to marine life, particularly octopus and squid species.

    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
     IconData
    -0.73
     Valer
    -0.71
    赦
    -0.70
     هاي
    -0.69
     XXV
    -0.69
    formas
    -0.68
    estacks
    -0.67
    ZIONI
    -0.67
     Republica
    -0.65
     feder
    -0.65
    POSITIVE LOGITS
     octopus
    3.19
     Octopus
    2.67
    octopus
    2.55
    Octopus
    2.45
     tentacles
    2.36
    🐙
    2.33
     squid
    2.28
     tenta
    2.17
     cep
    2.16
     Squid
    1.96
    Activations Density 0.045%

    No Known Activations