© 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. 48274
    Prev
    Next
    INDEX
    Explanations

    don't

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

    assign value, security

    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
     overrated
    0.50
     dump
    0.46
     реально
    0.46
     inkább
    0.44
    缛
    0.43
     வடக்கு
    0.43
     Dump
    0.42
     ভিসা
    0.41
     బహి
    0.41
     недостатки
    0.41
    POSITIVE LOGITS
     fragment
    0.43
     fragments
    0.42
    ora
    0.41
    ͜
    0.40
     Fragments
    0.38
    contents
    0.38
    Rewarded
    0.37
    Contents
    0.37
     njegova
    0.37
    χου
    0.37
    Activations Density 0.001%

    No Known Activations