© 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. 79737
    Prev
    Next
    INDEX
    Explanations

    getters and setters

    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
     TextAlign
    -1.26
    Podob
    -1.16
     Räume
    -1.12
     Unterschiede
    -1.06
     WaitForSeconds
    -1.05
    榇
    -1.02
    ࿚
    -1.02
     Unterscheidung
    -1.02
     Unterstützung
    -1.02
    が含ま
    -1.00
    POSITIVE LOGITS
     and
    0.94
    ❛
    0.93
    izadas
    0.93
    "';
    0.91
    vres
    0.88
    што
    0.88
     januari
    0.86
     glas
    0.86
     mList
    0.85
     fidd
    0.84
    Activations Density 0.022%

    No Known Activations