© 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. 208879
    Prev
    Next
    INDEX
    Explanations

    confirm your

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

    scoped, Vue, Stage, markets, addresses

    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
     xưa
    0.57
     factorización
    0.53
     売
    0.52
     théâtre
    0.52
     oficiais
    0.51
    दाबाद
    0.50
     postérieure
    0.50
     antérieure
    0.49
     préal
    0.49
     luyện
    0.49
    POSITIVE LOGITS
    纶
    0.50
     一个
    0.49
     diminutive
    0.49
     个
    0.48
     Covenant
    0.48
     individually
    0.48
     Species
    0.47
     Raz
    0.47
     Internal
    0.45
     Individual
    0.45
    Activations Density 0.000%

    No Known Activations