© 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. 34-GEMMASCOPE-RES-131K
    7. 64567
    Prev
    Next
    INDEX
    Explanations

    citations and academic papers

    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
     there
    -1.34
    There
    -1.34
     if
    -1.13
     never
    -1.12
     this
    -1.10
     or
    -1.10
    pée
    -1.07
     they
    -1.06
     had
    -1.05
     by
    -1.02
    POSITIVE LOGITS
     muita
    1.05
    มาณ
    1.04
    uristic
    1.02
    Споља
    1.00
     implor
    0.99
    êng
    0.95
    殍
    0.93
    стракт
    0.93
    andowski
    0.90
    árol
    0.90
    Activations Density 0.018%

    No Known Activations