© 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. 34-GEMMASCOPE-RES-131K
    7. 62895
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
     got
    -1.34
     really
    -1.29
     giving
    -1.28
     putting
    -1.27
     trying
    -1.24
     even
    -1.23
     just
    -1.22
     get
    -1.19
     gets
    -1.16
     goes
    -1.14
    POSITIVE LOGITS
    ẕ
    1.07
     utilized
    1.03
    どのように
    0.99
     возможно
    0.97
    Utiliz
    0.96
    StatusCodes
    0.95
    亦
    0.94
     memorial
    0.94
     TOPIC
    0.93
    atively
    0.93
    Activations Density 0.136%

    No Known Activations