© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64648
    Prev
    Next
    INDEX
    Explanations

    transition looping

    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
     or
    -1.18
     I
    -1.13
     but
    -1.12
     who
    -1.10
     Their
    -1.09
     like
    -1.04
    而非
    -1.02
    iphery
    -1.01
    。“
    -0.99
     they
    -0.98
    POSITIVE LOGITS
    öte
    1.27
     péché
    1.09
    ">−
    1.06
     очень
    1.06
     silikon
    1.04
     disfrute
    1.04
     şeklinde
    1.03
     boissons
    1.02
    öst
    1.02
    ihnachts
    1.02
    Activations Density 0.078%

    No Known Activations