© 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. 10-GEMMASCOPE-RES-131K
    4. 110615
    Prev
    Next
    INDEX
    Explanations

    files, images, users, items

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

    function or method names in code that operate on or manipulate user-related or item-related objects.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    operatives
    -1.34
     semoga
    -1.29
    harusnya
    -1.28
     également
    -1.24
     nessun
    -1.23
    чил
    -1.20
    都被
    -1.15
    믄
    -1.13
     dair
    -1.13
    것은
    -1.13
    POSITIVE LOGITS
     by
    1.44
     various
    1.41
     on
    1.41
     as
    1.37
     including
    1.35
     generating
    1.34
     We
    1.32
     burgeoning
    1.32
     creating
    1.30
     normaux
    1.30
    Activations Density 0.033%

    No Known Activations