© 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. 196741
    Prev
    Next
    INDEX
    Explanations

    certificate

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

    The Goal

    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
     godzin
    0.59
    自行
    0.51
     mesti
    0.51
    仝
    0.51
     étape
    0.48
    quinazolin
    0.47
     столи
    0.47
     казіно
    0.46
    て
    0.46
     {}>,
    0.46
    POSITIVE LOGITS
     scavenging
    0.50
     data
    0.49
    pecies
    0.46
     subsistence
    0.46
     research
    0.45
     feed
    0.45
     feeding
    0.45
     species
    0.44
    ola
    0.44
    ontology
    0.44
    Activations Density 0.000%

    No Known Activations