© 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. 34652
    Prev
    Next
    INDEX
    Explanations

    override or alternatives

    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
     TWO
    -0.82
     कोशिश
    -0.80
     memenuhi
    -0.79
     нови
    -0.76
     Andrew
    -0.75
     крайней
    -0.75
     edgy
    -0.74
    了两
    -0.74
     diberi
    -0.73
     vọng
    -0.73
    POSITIVE LOGITS
     rather
    0.98
     instead
    0.97
     rid
    0.91
    removeChild
    0.89
     disregard
    0.88
    dismiss
    0.87
     những
    0.86
     kapture
    0.84
    CLUDE
    0.84
     dissu
    0.84
    Activations Density 0.077%

    No Known Activations