© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9290
    Prev
    Next
    INDEX
    Explanations

    proper nouns and sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite

    user prompts, instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adap
    0.41
     uppercase
    0.41
    "]))
    0.40
     fittings
    0.40
     enfoc
    0.40
     fitted
    0.39
     envy
    0.39
     calcul
    0.39
     relays
    0.39
     memainkan
    0.39
    POSITIVE LOGITS
     ​
    0.61
     ​​​​
    0.59
    .​
    0.56
    .​​
    0.52
     ​​
    0.51
    -​
    0.44
    ,​
    0.42
    医
    0.40
    、​
    0.40
     Sovere
    0.39
    Activations Density 0.029%

    No Known Activations