© 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. 111816
    Prev
    Next
    INDEX
    Explanations

    science, valve, immediate

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

    social communication and broad topics

    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
     olduğunu
    0.49
    =?";
    0.49
     decontamination
    0.48
     condemnation
    0.48
     fillets
    0.47
     يتيمه
    0.46
    canonical
    0.46
     odnosu
    0.45
     putative
    0.45
     semantic
    0.44
    POSITIVE LOGITS
    Mir
    0.50
    eek
    0.50
    Living
    0.49
    Jersey
    0.47
    Chicago
    0.47
    Mango
    0.47
    !
    0.47
    Flor
    0.46
    Code
    0.46
    Club
    0.46
    Activations Density 0.000%

    No Known Activations