© 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. 237923
    Prev
    Next
    INDEX
    Explanations

    castles and villas

    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
     новая
    0.43
    xFF
    0.43
    +{
    0.43
    assisted
    0.41
    ɬ
    0.41
     adjuvant
    0.41
    ₸
    0.41
    FORMATION
    0.41
    ىل
    0.40
    pgamma
    0.40
    POSITIVE LOGITS
     évo
    0.50
    湎
    0.49
    ocurrencies
    0.48
     позво
    0.48
    ตัวเอง
    0.48
     pozwoli
    0.48
     دنی
    0.47
     допусти
    0.46
    तो
    0.46
     vague
    0.46
    Activations Density 0.002%

    No Known Activations