© 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. 118954
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

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

    Django migration operations or class names in code, particularly "AlterField", "AddField", and similar database schema modification commands.

    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
    when
    -2.84
    after
    -2.53
     öff
    -2.28
     sogen
    -2.23
     verbess
    -2.20
    最好的
    -2.17
    焄
    -2.13
     selben
    -2.11
    嗚
    -2.06
     Allgemeinen
    -2.03
    POSITIVE LOGITS
     to
    2.94
    蘩
    2.80
    ⬈
    2.44
    .
    2.36
    鐿
    2.34
    ES
    2.34
    媜
    2.34
    ᵉ
    2.30
     и
    2.25
    鼍
    2.20
    Activations Density 0.002%

    No Known Activations