© 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. 33953
    Prev
    Next
    INDEX
    Explanations

    past tense actions or states

    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
    😲
    -1.31
    👀
    -1.20
    🤔
    -1.16
     ❖
    -1.14
    🧐
    -1.09
    😱
    -1.09
    😣
    -1.08
    🥴
    -1.06
    🤨
    -1.06
    🤭
    -1.06
    POSITIVE LOGITS
     last
    1.40
     recently
    1.29
     after
    1.26
     ocorreu
    1.26
     particularly
    1.23
     because
    1.22
     nennt
    1.19
     especially
    1.18
     aconteceu
    1.13
     Wednesday
    1.12
    Activations Density 0.061%

    No Known Activations