© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39048
    Prev
    Next
    INDEX
    Explanations

    referencing prior information

    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
    ENIX
    -0.93
     церков
    -0.91
     REALLY
    -0.90
    了几
    -0.90
    ResetPassword
    -0.88
    IZACIÓN
    -0.88
     videos
    -0.87
    olat
    -0.87
     Angels
    -0.86
    medaille
    -0.85
    POSITIVE LOGITS
     these
    2.77
     above
    2.58
    above
    1.96
     this
    1.74
    上述
    1.72
    上記
    1.70
     powy
    1.60
     acima
    1.59
     aforesaid
    1.55
    Above
    1.53
    Activations Density 0.051%

    No Known Activations