© 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. 123560
    Prev
    Next
    INDEX
    Explanations

    period of time

    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
    そういえば
    -1.43
    めっちゃ
    -1.30
     ـ
    -1.23
    ability
    -1.23
    っていますが
    -1.20
    7
    -1.20
    two
    -1.19
    ’
    -1.17
     liksom
    -1.16
     rajut
    -1.16
    POSITIVE LOGITS
     since
    1.59
    "../
    1.41
    ."
    1.40
     It
    1.38
    Več
    1.35
    ircut
    1.30
    ))).
    1.28
     pageable
    1.27
     convertView
    1.27
     takže
    1.26
    Activations Density 0.055%

    No Known Activations