© 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. 124112
    Prev
    Next
    INDEX
    Explanations

    related to firsts and deliveries

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

    sometimes preceding

    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
     _{
    0.51
     Approximate
    0.50
     ODE
    0.48
    ój
    0.47
    ik
    0.46
     AMA
    0.46
    \}.
    0.45
     bagi
    0.44
     Kval
    0.44
     Context
    0.44
    POSITIVE LOGITS
    на
    0.57
     innovación
    0.52
    נה
    0.49
    လေး
    0.47
     nuevas
    0.46
    掩
    0.46
    seller
    0.45
    ບ
    0.45
    waves
    0.45
    телни
    0.45
    Activations Density 0.000%

    No Known Activations