© 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. 90587
    Prev
    Next
    INDEX
    Explanations

    competition results followed by entities

    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
     losses
    -2.06
     loss
    -1.97
     Losses
    -1.65
     loses
    -1.63
    Losses
    -1.63
    loss
    -1.57
     Loss
    -1.51
    losses
    -1.43
    LOSS
    -1.41
     lost
    -1.30
    POSITIVE LOGITS
    sorry
    1.06
    **/
    1.00
    
    0.89
    ído
    0.88
    こない
    0.86
     débuts
    0.84
     kezd
    0.84
    anmar
    0.83
     pieds
    0.83
     nevera
    0.83
    Activations Density 0.018%

    No Known Activations