© 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. 22-GEMMASCOPE-RES-131K
    7. 47
    Prev
    Next
    INDEX
    Explanations

    describing something

    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_22/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
    1
    -2.63
    8
    -2.59
    2
    -2.53
    4
    -2.41
     lauded
    -2.30
    旆
    -2.28
     вопрос
    -2.22
    )
    -2.19
    </strong>
    -2.16
    樒
    -2.14
    POSITIVE LOGITS
    してしまった
    2.27
    骊
    2.22
     in
    2.16
     verwijzen
    2.16
    贻
    2.09
    涐
    2.03
     voegen
    2.03
    Примеча
    2.02
    m
    2.02
    琤
    2.00
    Activations Density 0.067%

    No Known Activations