© 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. 86871
    Prev
    Next
    INDEX
    Explanations

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ЦЕ
    -1.21
     Also
    -1.18
    をします
    -1.16
    を行います
    -1.14
    なぁ
    -1.11
    暱
    -1.10
    賬
    -1.08
    MENT
    -1.07
    なんだろう
    -1.05
     personalizar
    -1.05
    POSITIVE LOGITS
     of
    2.69
    ؜
    1.30
    𓐍
    1.14
     chance
    1.08
     leſs
    1.07
     COMPOUNDS
    1.06
     kapak
    1.05
     作り方
    1.04
    Frosty
    1.04
     kapas
    1.02
    Activations Density 0.051%

    No Known Activations