© 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. 228574
    Prev
    Next
    INDEX
    Explanations

    question formation

    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
    
    0.46
    ＞
    0.46
    ľov
    0.44
    ocial
    0.44
    𝚙
    0.42
    PERSON
    0.42
    creating
    0.41
    政
    0.41
    ascape
    0.41
     보내
    0.41
    POSITIVE LOGITS
     Spicy
    0.46
     ProRes
    0.46
     ChIP
    0.45
     soothing
    0.44
     isopropyl
    0.44
     Herring
    0.44
     Dark
    0.43
     Indy
    0.43
     corrobor
    0.43
     cockpit
    0.42
    Activations Density 0.000%

    No Known Activations