© 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. 31-GEMMASCOPE-2-RES-262K
    7. 104663
    Prev
    Next
    INDEX
    Explanations

    proven presence

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

    Store, hypothesis, conditions, humans, temperatures, observation

    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_31_width_262k_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
     RS
    0.51
    aram
    0.49
     R
    0.48
     RL
    0.48
     D
    0.48
    an
    0.47
     M
    0.47
     P
    0.47
     Ah
    0.47
     HN
    0.46
    POSITIVE LOGITS
    욌
    0.54
    ですが
    0.52
     குழந்தைகளுக்கு
    0.51
    であるが
    0.50
    ্্
    0.49
     Фурга
    0.48
     лого
    0.48
     ලි
    0.47
    🏄
    0.47
     uzav
    0.47
    Activations Density 0.000%

    No Known Activations