© 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. 192106
    Prev
    Next
    INDEX
    Explanations

    time remaining or elapsed

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

    time points and durations

    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
     variational
    0.44
    showerror
    0.44
     scrimmage
    0.42
    慗
    0.41
    넉
    0.40
    putExtra
    0.39
     ambayo
    0.38
     тях
    0.38
     onCreate
    0.37
     Inte
    0.37
    POSITIVE LOGITS
    เวลา
    0.49
     midway
    0.47
     عام
    0.45
     halfway
    0.45
    正在
    0.44
     देर
    0.44
     відбувається
    0.43
    ="*"
    0.43
     WEEK
    0.42
     तीस
    0.42
    Activations Density 0.035%

    No Known Activations