© 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. 119523
    Prev
    Next
    INDEX
    Explanations

    ingress, correo, gencia, incursion

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

    words related to entry, ingress, or coming into something.

    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
    and
    -3.06
    as
    -2.47
    on
    -2.47
    }$
    -2.44
    )$
    -2.28
    猻
    -2.23
    懨
    -2.22
     crave
    -2.20
    di
    -2.14
    必要な
    -2.13
    POSITIVE LOGITS
     komplette
    2.50
     offizielle
    2.33
     verbess
    2.28
     perfekte
    2.14
    鲮
    2.03
    仕方
    2.02
    跸
    2.02
     gesamte
    2.02
    WebElementEntity
    2.02
    魠
    2.00
    Activations Density 0.001%

    No Known Activations