© 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. 41253
    Prev
    Next
    INDEX
    Explanations

    ;

    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
    0
    -4.72
     После
    -3.86
     -
    -3.81
     After
    -3.80
     It
    -3.47
    2
    -3.47
     
    -3.41
     Before
    -3.41
    1
    -3.38
    3
    -3.34
    POSITIVE LOGITS
    s
    4.34
    歘
    3.92
    鮡
    3.42
    埽
    3.39
    ⑊
    3.36
    箧
    3.34
    踯
    3.34
    🫢
    3.34
    ;
    3.31
    ſſi
    3.31
    Activations Density 0.007%

    No Known Activations