© 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. 97941
    Prev
    Next
    INDEX
    Explanations

    allow them

    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
    angka
    -0.82
    عار
    -0.82
    霜
    -0.80
    град
    -0.77
    relations
    -0.77
    ösen
    -0.75
    ousse
    -0.74
     доби
    -0.74
    rageous
    -0.73
     yelled
    -0.73
    POSITIVE LOGITS
    cline
    1.51
     LIABLE
    0.80
     Decline
    0.79
     kolei
    0.77
    把它
    0.75
    Hed
    0.73
     alquiler
    0.71
     explotación
    0.70
     IMPLIED
    0.68
    auder
    0.68
    Activations Density 0.002%

    No Known Activations