© 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. 86545
    Prev
    Next
    INDEX
    Explanations

    number 26

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

    numbers and dates

    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
    ânea
    0.39
    عية
    0.38
    unto
    0.38
    דע
    0.38
     hice
    0.37
    颔
    0.37
    ورو
    0.37
     Pendant
    0.37
     PVP
    0.37
    читься
    0.36
    POSITIVE LOGITS
     পৃ
    0.40
     Buchstaben
    0.40
     recalling
    0.39
    Vh
    0.39
    ഴു
    0.37
     શું
    0.36
     Atra
    0.36
     %).
    0.36
     stepping
    0.35
     weakly
    0.35
    Activations Density 0.021%

    No Known Activations