© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101420
    Prev
    Next
    INDEX
    Explanations

    octopus and squid

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

    words relating to cephalopods including octopus, squid, and similar sea creatures.

    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
    This
    -2.06
    S
    -1.80
    遢
    -1.78
    après
    -1.73
    It
    -1.66
    缫
    -1.64
    ro
    -1.64
    A
    -1.63
     حول
    -1.62
     Vedi
    -1.59
    POSITIVE LOGITS
     to
    1.99
    }
    1.83
    section
    1.80
    ’)
    1.77
    ()],
    1.61
    bluza
    1.59
    \\
    1.54
    邶
    1.53
    }\
    1.48
    </h2>
    1.46
    Activations Density 0.012%

    No Known Activations