© 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. 42111
    Prev
    Next
    INDEX
    Explanations

    old followed by a name

    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_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
     recrutement
    -2.02
     konkrete
    -2.00
    锖
    -1.91
    िंग
    -1.91
     возможность
    -1.88
    QMetaType
    -1.86
    踽
    -1.84
     хорошие
    -1.83
    stuffed
    -1.83
     perfekte
    -1.83
    POSITIVE LOGITS
    y
    2.91
    na
    2.56
    an
    2.52
    s
    2.41
     Now
    2.38
     invariably
    2.33
    en
    2.30
     exceptionally
    2.27
    на
    2.22
     About
    2.22
    Activations Density 0.008%

    No Known Activations