© 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. 65702
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks and appreciation

    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
     только
    -1.23
     функция
    -1.16
     höl
    -1.12
     adecuada
    -1.08
    ônia
    -1.06
     tell
    -1.06
    *}[
    -1.02
     опас
    -1.02
    :
    -1.01
    indari
    -0.99
    POSITIVE LOGITS
    Nodo
    1.15
    暧
    1.14
    视线
    1.14
    Thro
    1.13
     къде
    1.11
    𐐪
    1.10
     eletrônico
    1.10
     elétrico
    1.09
    Rusia
    1.07
    eció
    1.06
    Activations Density 0.001%

    No Known Activations