© 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. 80980
    Prev
    Next
    INDEX
    Explanations

    can't work out

    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
     plutôt
    -1.40
     möglichst
    -1.36
     rather
    -1.20
     instead
    -1.10
     максимально
    -1.09
    こそ
    -1.07
     piuttosto
    -1.06
     somewhat
    -1.02
     максима
    -1.00
     fiecare
    -1.00
    POSITIVE LOGITS
     anymore
    2.78
     nor
    2.55
     without
    1.89
     any
    1.85
     anything
    1.76
     إلا
    1.70
     because
    1.69
    nor
    1.64
     unless
    1.63
     אלא
    1.50
    Activations Density 0.130%

    No Known Activations