© 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. 156625
    Prev
    Next
    INDEX
    Explanations

    urban areas and criteria for

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

    flawed approach

    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
     Tillman
    0.52
    ط
    0.50
    和你
    0.49
    ка
    0.49
    фа
    0.47
     Pohl
    0.47
    闫
    0.47
    恳
    0.47
    荣誉
    0.47
    க்கில்
    0.46
    POSITIVE LOGITS
     musk
    0.50
     resonant
    0.50
     gun
    0.49
     diaper
    0.47
     শক্তি
    0.46
     stator
    0.46
     diuretic
    0.46
     आकार
    0.46
     detectable
    0.45
     mammals
    0.45
    Activations Density 0.001%

    No Known Activations